auto: new LLM security papers (run #17) by github-actions[bot] · Pull Request #48 · emmanuelgjr/GenAI-Security-Literature-Review

github-actions · 2026-07-19T08:14:24Z

Automated Paper Fetch

New papers discovered from arXiv, Semantic Scholar, and CrossRef.

All entries are marked reviewed: false -- please review before merging.

New Entries

--- New Entries ---
- [llmsec-2026-00206] Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation
  https://arxiv.org/abs/2607.14493
  Categories: prompt-injection
- [llmsec-2026-00207] PVDetector: Detecting Prompt Injection Attacks on Purpose-Specific LLM Agents through Policy-Violation Concept Analysis
  https://arxiv.org/abs/2607.12624
  Categories: prompt-injection, guardrails
- [llmsec-2026-00208] Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls
  https://arxiv.org/abs/2607.09076
  Categories: agentic-threats, monitoring-detection
- [llmsec-2026-00209] When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents
  https://arxiv.org/abs/2607.06595
  Categories: memory-security
- [llmsec-2026-00210] Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning
  https://arxiv.org/abs/2607.01138
  Categories: agentic-threats
- [llmsec-2026-00211] A Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open Problems
  https://arxiv.org/abs/2606.31639
  Categories: autonomous-operations, survey
- [llmsec-2026-00212] Toward Secure and Reliable PDDL Formalization of Large Language Models with Planner-in-the-Loop Feedback
  https://arxiv.org/abs/2606.29700
  Categories: benchmarks
- [llmsec-2026-00213] An Empirical Evaluation of Prompt Injection Vulnerabilities in Large Language Models Across Multilingual and Obfuscated Attack Scenarios
  https://arxiv.org/abs/2606.29602
  Categories: prompt-injection
- [llmsec-2026-00214] Memory as an Attack Surface in LLM Agents: A Study on Multiple-Choice Question Answering
  https://arxiv.org/abs/2606.29030
  Categories: tool-use-security
- [llmsec-2026-00215] FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks
  https://arxiv.org/abs/2606.28962
  Categories: data-poisoning
- [llmsec-2026-00216] RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots
  https://arxiv.org/abs/2606.28649
  Categories: prompt-injection
- [llmsec-2026-00217] Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models
  https://arxiv.org/abs/2606.28153
  Categories: jailbreaking, guardrails
- [llmsec-2026-00218] LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity
  https://arxiv.org/abs/2606.28450
  Categories: survey
- [llmsec-2026-00219] Representation Matters: An Empirical Study of Program Representations for LLM Vulnerability Reasoning
  https://arxiv.org/abs/2606.25356
  Categories: benchmarks
- [llmsec-2026-00220] HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
  https://arxiv.org/abs/2606.24819
  Categories: benchmarks
- [llmsec-2026-00221] Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
  https://arxiv.org/abs/2606.24322
  Categories: memory-security
- [llmsec-2026-00222] Evaluating LLMs for Real-World Web Vulnerability Detection
  https://arxiv.org/abs/2606.21397
  Categories: benchmarks
- [llmsec-2026-00223] Local LLM Agents as Vulnerable Runtimes:A Source-Code Audit of the Agent Runtime Layer
  https://arxiv.org/abs/2606.21071
  Categories: prompt-injection
- [llmsec-2026-00224] Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
  https://arxiv.org/abs/2606.21037
  Categories: benchmarks
- [llmsec-2026-00225] Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software
  https://arxiv.org/abs/2606.20502
  Categories: benchmarks
- [llmsec-2026-00226] Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems
  https://arxiv.org/abs/2607.14611
  Categories: prompt-injection, agentic-threats, sandboxing-isolation
- [llmsec-2026-00227] Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation
  https://arxiv.org/abs/2607.13987
  Categories: prompt-injection, threat-modeling
- [llmsec-2026-00228] How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
  https://arxiv.org/abs/2607.13718
  Categories: prompt-injection, agentic-threats, access-control
- [llmsec-2026-00229] Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels
  https://arxiv.org/abs/2607.12792
  Categories: jailbreaking, benchmarks
- [llmsec-2026-00230] Breaking Refusal in the First Half: A Mechanistic Study of the Prefill Jailbreak
  https://arxiv.org/abs/2607.14147
  Categories: jailbreaking
- [llmsec-2026-00231] SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classification
  https://arxiv.org/abs/2607.13081
  Categories: prompt-injection, agentic-threats, guardrails, benchmarks
- [llmsec-2026-00232] Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud
  https://arxiv.org/abs/2607.10712
  Categories: data-poisoning
- [llmsec-2026-00233] NetInjectBench: Benchmarking Indirect Prompt Injection in Tool-Using Large Language Model Agents for Network Operations
  https://arxiv.org/abs/2607.10490
  Categories: prompt-injection, benchmarks, tool-use-security
- [llmsec-2026-00234] Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices
  https://arxiv.org/abs/2607.10269
  Categories: prompt-injection
- [llmsec-2026-00235] Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety
  https://arxiv.org/abs/2607.10112
  Categories: jailbreaking, guardrails, benchmarks
- [llmsec-2026-00236] Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models
  https://arxiv.org/abs/2607.08282
  Categories: agent-architecture
- [llmsec-2026-00237] Prismata: Confining Cross-Site Prompt Injection in Web Agents
  https://arxiv.org/abs/2607.08147
  Categories: prompt-injection
- [llmsec-2026-00238] Efficient Safety Alignment of Language Models via Latent Personality Traits
  https://arxiv.org/abs/2607.07918
  Categories: adversarial-examples, guardrails
- [llmsec-2026-00239] Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
  https://arxiv.org/abs/2607.07903
  Categories: jailbreaking, adversarial-examples
- [llmsec-2026-00240] Open Models, Open Risks: Measuring Unsafe Generation in Text-to-Image Models In the Wild
  https://arxiv.org/abs/2607.07827
  Categories: jailbreaking
- [llmsec-2026-00241] Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting
  https://arxiv.org/abs/2607.07433
  Categories: prompt-injection, agentic-threats, threat-modeling
- [llmsec-2026-00242] Untrusted Content Masking for Web Agents with Security Guarantees
  https://arxiv.org/abs/2607.05277
  Categories: prompt-injection
- [llmsec-2026-00243] Agent Data Injection Attacks are Realistic Threats to AI Agents
  https://arxiv.org/abs/2607.05120
  Categories: prompt-injection, agentic-threats
- [llmsec-2026-00244] DualView: Preventing Indirect Prompt Injection in Personal AI Agents
  https://arxiv.org/abs/2607.03821
  Categories: prompt-injection
- [llmsec-2026-00245] Overloading Large Vision-Language Models for Jailbreaking
  https://arxiv.org/abs/2607.02961
  Categories: jailbreaking
- [llmsec-2026-00246] HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment
  https://arxiv.org/abs/2607.00572
  Categories: jailbreaking, guardrails
- [llmsec-2026-00247] Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces
  https://arxiv.org/abs/2607.00481
  Categories: jailbreaking
- [llmsec-2026-00248] Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
  https://arxiv.org/abs/2606.31227
  Categories: red-teaming
- [llmsec-2026-00249] Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense
  https://arxiv.org/abs/2606.30783
  Categories: prompt-injection, benchmarks
- [llmsec-2026-00250] Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
  https://arxiv.org/abs/2606.30755
  Categories: agentic-threats, benchmarks
- [llmsec-2026-00251] Forensic Trajectory Signatures for Agent Memory Poisoning Detection
  https://arxiv.org/abs/2606.30566
  Categories: memory-security
- [llmsec-2026-00252] On the Inseparability of Instructions and Data in Shared-Embedding Sequence Models
  https://arxiv.org/abs/2606.27567
  Categories: prompt-injection, access-control
- [llmsec-2026-00253] Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries
  https://arxiv.org/abs/2606.26936
  Categories: jailbreaking
- [llmsec-2026-00254] MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG
  https://arxiv.org/abs/2606.26793
  Categories: prompt-injection, agentic-threats, red-teaming, benchmarks
- [llmsec-2026-00255] Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
  https://arxiv.org/abs/2606.26627
  Categories: survey
- [llmsec-2026-00256] Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models
  https://arxiv.org/abs/2606.26566
  Categories: jailbreaking, benchmarks, survey, threat-modeling
- [llmsec-2026-00257] Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
  https://arxiv.org/abs/2606.26479
  Categories: prompt-injection, benchmarks
- [llmsec-2026-00258] RAS: Measuring LLM Safety Through Refusal Alignment
  https://arxiv.org/abs/2606.25750
  Categories: jailbreaking, guardrails
- [llmsec-2026-00259] How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring
  https://arxiv.org/abs/2606.25487
  Categories: prompt-injection, jailbreaking
- [llmsec-2026-00260] PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation
  https://arxiv.org/abs/2606.24081
  Categories: jailbreaking, benchmarks
- [llmsec-2026-00261] TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
  https://arxiv.org/abs/2606.23496
  Categories: jailbreaking, red-teaming
- [llmsec-2026-00262] Detecting Malicious Agent Skills in the Wild using Attention
  https://arxiv.org/abs/2606.23416
  Categories: agentic-threats
- [llmsec-2026-00263] DE-FIVE: Detecting Malicious Image Prompts via Fourier Features and Image Vector Embeddings
  https://arxiv.org/abs/2606.22779
  Categories: prompt-injection, adversarial-examples
- [llmsec-2026-00264] The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
  https://arxiv.org/abs/2606.22686
  Categories: guardrails
- [llmsec-2026-00265] Confidently Wrong: Severity-Aware Calibration of Prompt-Injection Detectors under Attack Shift
  https://arxiv.org/abs/2606.22659
  Categories: benchmarks
- [llmsec-2026-00266] Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
  https://arxiv.org/abs/2606.21732
  Categories: prompt-injection
- [llmsec-2026-00267] Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
  https://arxiv.org/abs/2607.01153
  Categories: agentic-threats, benchmarks
- [llmsec-2026-00268] Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
  https://arxiv.org/abs/2606.27632
  Categories: tool-use-security
- [llmsec-2026-00269] MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety
  https://arxiv.org/abs/2606.02630
  Categories: jailbreaking, adversarial-examples
- [llmsec-2026-00270] AI Security Research Should Better Incentivize Defense Research
  https://arxiv.org/abs/2605.23448
  Categories: membership-inference, federated-learning
- [llmsec-2026-00271] The Poisoned Chalice of LLM Evaluation Report
  https://arxiv.org/abs/2607.07481
  Categories: benchmarks
- [llmsec-2026-00272] ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models
  https://arxiv.org/abs/2607.00361
  Categories: data-poisoning
- [llmsec-2026-00273] Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language Models
  https://arxiv.org/abs/2606.30899
  Categories: data-poisoning
- [llmsec-2026-00274] Theory of Continual Learning Against Data Poisoning Attacks
  https://arxiv.org/abs/2606.29841
  Categories: data-poisoning
- [llmsec-2026-00275] Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare
  https://arxiv.org/abs/2606.28666
  Categories: agentic-threats
- [llmsec-2026-00276] When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems
  https://arxiv.org/abs/2606.27511
  Categories: federated-learning
- [llmsec-2026-00277] Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
  https://arxiv.org/abs/2606.26036
  Categories: data-poisoning
- [llmsec-2026-00278] Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
  https://arxiv.org/abs/2606.25115
  Categories: agentic-threats
- [llmsec-2026-00279] LLM-Based Scientific Peer Review: Methods, Benchmarks, and Reliability Challenges
  https://arxiv.org/abs/2606.25057
  Categories: benchmarks, survey
- [llmsec-2026-00280] When Does Belief-Based Agent Memory Help? Reliability-Conditional Updating and Provenance-Capped Poisoning Defense
  https://arxiv.org/abs/2606.22030
  Categories: benchmarks
- [llmsec-2026-00281] Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
  https://arxiv.org/abs/2606.20922
  Categories: prompt-injection
- [llmsec-2026-00282] A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots
  https://arxiv.org/abs/2606.19660
  Categories: prompt-injection, input-filtering
- [llmsec-2026-00283] SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents
  https://arxiv.org/abs/2606.18356
  Categories: agentic-threats, sandboxing-isolation, benchmarks
- [llmsec-2026-00284] The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements
  https://arxiv.org/abs/2606.12797
  Categories: agentic-threats
- [llmsec-2026-00285] Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
  https://arxiv.org/abs/2606.10846
  Categories: data-poisoning
- [llmsec-2026-00286] MemVenom: Triggered Poisoning of Multimodal Memories in Web Agents
  https://arxiv.org/abs/2606.10742
  Categories: memory-security
- [llmsec-2026-00287] Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs
  https://arxiv.org/abs/2606.10322
  Categories: agent-architecture
- [llmsec-2026-00288] Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
  https://arxiv.org/abs/2606.07970
  Categories: adversarial-examples, guardrails
- [llmsec-2026-00289] Steering Vectors are an Adversarial Attack Surface
  https://arxiv.org/abs/2606.05958
  Categories: jailbreaking, data-poisoning, adversarial-examples
- [llmsec-2026-00290] Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
  https://arxiv.org/abs/2606.05743
  Categories: jailbreaking, guardrails
- [llmsec-2026-00291] Patcher: Post-Hoc Patching of Backdoored Large Language Models
  https://arxiv.org/abs/2606.02995
  Categories: jailbreaking, data-poisoning, guardrails
- [llmsec-2026-00292] BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
  https://arxiv.org/abs/2606.02947
  Categories: data-poisoning
- [llmsec-2026-00293] Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
  https://arxiv.org/abs/2605.29960
  Categories: memory-security
- [llmsec-2026-00294] When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries
  https://arxiv.org/abs/2606.28332
  Categories: guardrails, benchmarks
- [llmsec-2026-00295] Cordyceps: Covert Control Attacks on LLMs via Data Poisoning
  https://arxiv.org/abs/2605.26595
  Categories: data-poisoning, monitoring-detection
- [llmsec-2026-00296] GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
  https://arxiv.org/abs/2605.26574
  Categories: data-poisoning
- [llmsec-2026-00297] Security of OpenClaw Agents: Fundamentals, Attacks, and Countermeasures
  https://arxiv.org/abs/2605.25435
  Categories: autonomous-operations
- [llmsec-2026-00298] Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions
  https://arxiv.org/abs/2605.25073
  Categories: data-poisoning, fine-tuning-security, survey
- [llmsec-2026-00299] When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents
  https://arxiv.org/abs/2605.24069
  Categories: benchmarks
- [llmsec-2026-00300] Backdooring Masked Diffusion Language Models
  https://arxiv.org/abs/2605.19262
  Categories: data-poisoning
- [llmsec-2026-00301] Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
  https://arxiv.org/abs/2605.19147
  Categories: data-poisoning
- [llmsec-2026-00302] Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks
  https://arxiv.org/abs/2605.18988
  Categories: agentic-threats, guardrails, autonomous-operations
- [llmsec-2026-00303] Not What You Asked For: Typographic Attacks in Household Robot Manipulation
  https://arxiv.org/abs/2605.18593
  Categories: benchmarks
- [llmsec-2026-00304] OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
  https://arxiv.org/abs/2605.18930
  Categories: agentic-threats
- [llmsec-2026-00305] Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
  https://arxiv.org/abs/2605.15338
  Categories: memory-security
- [llmsec-2026-00306] Ground-Side Mission Plan Compilation with Policy-as-Code Guardrails for Cloud-Native Satellite Platforms
  https://arxiv.org/abs/2607.14798
  Categories: guardrails
- [llmsec-2026-00307] Democratizing Agent Deployment Safety: A Structural Monitoring Approach
  https://arxiv.org/abs/2607.14570
  Categories: monitoring-detection
- [llmsec-2026-00308] Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration
  https://arxiv.org/abs/2607.12662
  Categories: agentic-threats
- [llmsec-2026-00309] Agentic Service-Oriented Computing: A Manifesto for the Next Frontier of Service-Oriented Computing
  https://arxiv.org/abs/2607.12619
  Categories: agentic-threats, autonomous-operations
- [llmsec-2026-00310] Beyond Test Presence: Assessing the Quality and Robustness of Agent-Generated Tests in Open-Source Projects
  https://arxiv.org/abs/2607.12068
  Categories: benchmarks
- [llmsec-2026-00311] Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation
  https://arxiv.org/abs/2607.11288
  Categories: agentic-threats
- [llmsec-2026-00312] VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents
  https://arxiv.org/abs/2607.09653
  Categories: agent-architecture
- [llmsec-2026-00313] SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
  https://arxiv.org/abs/2607.08681
  Categories: agentic-threats, benchmarks, autonomous-operations
- [llmsec-2026-00314] Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring
  https://arxiv.org/abs/2607.08066
  Categories: jailbreaking, monitoring-detection
- [llmsec-2026-00315] Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety
  https://arxiv.org/abs/2607.07695
  Categories: red-teaming, benchmarks, agent-architecture
- [llmsec-2026-00316] Multi-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
  https://arxiv.org/abs/2607.07368
  Categories: agent-architecture
- [llmsec-2026-00317] Security and Privacy in Agentic AI: Grand Challenges and Future Directions
  https://arxiv.org/abs/2607.06608
  Categories: agentic-threats
- [llmsec-2026-00318] The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities
  https://arxiv.org/abs/2607.05743
  Categories: access-control, sandboxing-isolation, human-in-the-loop
- [llmsec-2026-00319] aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents
  https://arxiv.org/abs/2607.05518
  Categories: access-control
- [llmsec-2026-00320] LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems
  https://arxiv.org/abs/2607.09756
  Categories: agentic-threats, monitoring-detection
- [llmsec-2026-00321] CAGE-1: Control, Assurance, and Governance Evaluation for Enterprise Agentic AI
  https://arxiv.org/abs/2607.03510
  Categories: agentic-threats
- [llmsec-2026-00322] Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies
  https://arxiv.org/abs/2607.03423
  Categories: guardrails
- [llmsec-2026-00323] Agentic-SecPBFT: Agentic AI-Driven Proactive Security Framework for Wireless PBFT Consensus in Mobile Ad-Hoc Networks
  https://arxiv.org/abs/2607.03269
  Categories: agentic-threats
- [llmsec-2026-00324] Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
  https://arxiv.org/abs/2607.02376
  Categories: agentic-threats
- [llmsec-2026-00325] Copewell: A Multi-Agent Swarm Architecture for Equitable Mental Wellness Support
  https://arxiv.org/abs/2607.02245
  Categories: agent-architecture
- [llmsec-2026-00326] Janus: a Playground for User-Involved Agentic Permission Management
  https://arxiv.org/abs/2607.01510
  Categories: agentic-threats
- [llmsec-2026-00327] An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping
  https://arxiv.org/abs/2606.31831
  Categories: agentic-threats
- [llmsec-2026-00328] Verification-Gated Agentic Mission-State Governance for Intelligent Industrial Multi-Robot Systems
  https://arxiv.org/abs/2606.31339
  Categories: agentic-threats
- [llmsec-2026-00329] Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
  https://arxiv.org/abs/2606.28425
  Categories: agentic-threats, agent-architecture, tool-use-security, autonomous-operations
- [llmsec-2026-00330] The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
  https://arxiv.org/abs/2606.26057
  Categories: output-moderation, guardrails, access-control
- [llmsec-2026-00331] Identity Management for Agentic AI: The new frontier of authorization, authentication, and security for an AI agent world
  https://www.semanticscholar.org/paper/c482e9aa341ecd5dbf545aa16df9c6815aa55650
  Categories: agentic-threats, access-control, autonomous-operations
- [llmsec-2026-00332] TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
  https://www.semanticscholar.org/paper/753736d18fa9bf3ed730836b30b89bf5653cd8dd
  Categories: agentic-threats, agent-architecture
- [llmsec-2026-00333] SAGA: A Security Architecture for Governing AI Agentic Systems
  https://www.semanticscholar.org/paper/643e64fd77cb9a2b2defd63769af75a92365a6c7
  Categories: agentic-threats, access-control
- [llmsec-2026-00334] Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems
  https://www.semanticscholar.org/paper/fa748fc17c5e7506bf3fed331e81b2011e5039d0
  Categories: agentic-threats, autonomous-operations
- [llmsec-2026-00335] Agentic AI for 6G: A New Paradigm for Autonomous RAN Security Compliance
  https://www.semanticscholar.org/paper/3db949389086da9db5ec5e9fc88c1de41ee99df2
  Categories: agentic-threats
- [llmsec-2026-00336] ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications
  https://www.semanticscholar.org/paper/37c56b578604d3dea4d86ae9bf1a76cdbff5129e
  Categories: prompt-injection, agentic-threats, threat-modeling
- [llmsec-2026-00337] Security Analysis of Agentic AI Communication Protocols: A Comparative Evaluation
  https://www.semanticscholar.org/paper/a380e368fc630cdeab758fa86959a7570024a7a3
  Categories: agentic-threats, benchmarks, agent-architecture
- [llmsec-2026-00338] Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation
  https://www.semanticscholar.org/paper/7ef12e7f28b538a044f3b2c2af4160446723a200
  Categories: supply-chain-attacks, agentic-threats
- [llmsec-2026-00339] AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
  https://www.semanticscholar.org/paper/8f66f06304829890f83c428fb4677a54c91d9fbd
  Categories: agentic-threats, guardrails, tool-use-security
- [llmsec-2026-00340] AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
  https://www.semanticscholar.org/paper/27d50468f1016b18c07283b56ea5dc0f5479b980
  Categories: guardrails
- [llmsec-2026-00341] A Research Landscape of Agentic AI and Large Language Models: Applications, Challenges and Future Directions
  https://www.semanticscholar.org/paper/24ae03b3f1793dc2ca5aec06ed4c50ec61a6c7cd
  Categories: agentic-threats
- [llmsec-2026-00342] Building A Secure Agentic AI Application Leveraging Google’s A2A Protocol
  https://www.semanticscholar.org/paper/8f3fc962d61ac1d298ed511ba27272f1c5991599
  Categories: agentic-threats, agent-architecture
- [llmsec-2026-00343] A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control
  https://www.semanticscholar.org/paper/2bbf1fc0d7bce53edbfcaeb81143c1233c074923
  Categories: agentic-threats, access-control
- [llmsec-2026-00344] Trustworthy agentic AI systems: a cross-layer review of architectures, threat models, and governance strategies for real-world deployment
  https://www.semanticscholar.org/paper/b4578b31671f32a11e47b0f4870b885f55900153
  Categories: agentic-threats, threat-modeling
- [llmsec-2026-00345] Agent-Based AI Approach to Security in IoT Systems Leveraging Genai
  https://www.semanticscholar.org/paper/6f1174d046152d8270662e216a28d82016aed238
  Categories: agentic-threats
- [llmsec-2026-00346] Sola-Visibility-ISPM: Benchmarking Agentic AI for Identity Security Posture Management Visibility
  https://www.semanticscholar.org/paper/ec53bf26de1b0055611062408c1116f35cd308e7
  Categories: agentic-threats, benchmarks
- [llmsec-2026-00347] Oversight Structures for Agentic AI in Public-Sector Organizations
  https://www.semanticscholar.org/paper/f28ed25afc2d23d9d62e0766b2956d142bb9913a
  Categories: agentic-threats
- [llmsec-2026-00348] Formal Analysis and Supply Chain Security for Agentic AI Skills
  https://www.semanticscholar.org/paper/d6665127102362bd5060d673a21fe6b1de3f376c
  Categories: supply-chain-attacks, agentic-threats
- [llmsec-2026-00349] Security in the Age of AI Teammates: An Empirical Study of Agentic Pull Requests on GitHub
  https://www.semanticscholar.org/paper/53ed867f0c124539c1521dec5d052779cb8a0f2a
  Categories: agentic-threats
- [llmsec-2026-00350] Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
  https://www.semanticscholar.org/paper/e7ce3289d680295e57dc66ad0563924e2006cd3a
  Categories: agentic-threats, tool-use-security, survey
- [llmsec-2026-00351] AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems
  https://www.semanticscholar.org/paper/4e4919e0bc5033dbccb1e837605d0762cb769f00
  Categories: agentic-threats, human-in-the-loop
- [llmsec-2026-00352] Human Society-Inspired Approaches to Agentic AI Security: The 4C Framework
  https://www.semanticscholar.org/paper/20f1c57301375e2642fd4969713acdf7c20177b6
  Categories: agentic-threats
- [llmsec-2026-00353] AGENTIC AI AND CYBER SECURITY: AUTONOMOUS THREAT HUNTING, INTRUSION DETECTION, AND ADAPTIVE DEFENSE MECHANISMS IN A WORLD OF INCREASINGLY SOPHISTICATED CYBER ATTACKS
  https://www.semanticscholar.org/paper/341d785475da2663203fc3ccaa1bca71968310bb
  Categories: agentic-threats
- [llmsec-2026-00354] Automating Organizational Cyber Security Policy Compliance Against Industry Standards Using Agentic AI
  https://www.semanticscholar.org/paper/b675c553acbc44d29e06bb0c8155978a0cbf73c7
  Categories: agentic-threats, audit-assurance
- [llmsec-2026-00355] Sentinel Agents for Secure and Trustworthy Agentic AI in Multi-Agent Systems
  https://www.semanticscholar.org/paper/296c6954e9fe7e5b48fe2dfadc6a23b4310b1bab
  Categories: agentic-threats, monitoring-detection, agent-architecture
- [llmsec-2026-00356] Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System
  https://www.semanticscholar.org/paper/f42a56937c1a50380c6143ba835efa5b97c5c31e
  Categories: agentic-threats, monitoring-detection, autonomous-operations, threat-modeling
- [llmsec-2026-00357] Security Risks of Agentic Vehicles: A Systematic Analysis of Cognitive and Cross-Layer Threats
  https://www.semanticscholar.org/paper/af6ea3b929b3a1aba976f3d48d2c6d040968e7e0
  Categories: agentic-threats
- [llmsec-2026-00358] QSAF: A Novel Mitigation Framework for Cognitive Degradation in Agentic AI
  https://www.semanticscholar.org/paper/c3da993174d74465fbb632f2d3de5c31d8b58a26
  Categories: prompt-injection, agentic-threats
- [llmsec-2026-00359] Agent Security is a Systems Problem
  https://www.semanticscholar.org/paper/44d178dd44370773c5d0536025c8c848febcee9b
  Categories: agentic-threats
- [llmsec-2026-00360] In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers
  https://www.semanticscholar.org/paper/8b9011b256c4819d47721efc3f9522a721b92735
  Categories: prompt-injection, agentic-threats
- [llmsec-2026-00361] MobiLLM: An Agentic AI Framework for Closed-Loop Threat Mitigation in 6G Open RANs
  https://www.semanticscholar.org/paper/3fb886ee2cfed48af9dd1766725f0385754e5528
  Categories: agentic-threats
- [llmsec-2026-00362] The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines
  https://www.semanticscholar.org/paper/6417c2e047247e4e844c8ab390fb3812fb4f80e1
  Categories: agentic-threats, agent-architecture
- [llmsec-2026-00363] Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems
  https://www.semanticscholar.org/paper/7e92cdb5bab66d182dd0abda4ce6bb8ccf8b75cf
  Categories: agentic-threats, benchmarks
- [llmsec-2026-00364] Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture
  https://www.semanticscholar.org/paper/783db6d7e129f598539e38b4608dfec1702c0eb1
  Categories: agentic-threats, agent-architecture
- [llmsec-2026-00365] AgentCyTE: Leveraging Agentic AI to Generate Cybersecurity Training & Experimentation Scenarios
  https://www.semanticscholar.org/paper/b89b1dc9130393a3c3d31d59f31897323f73d7eb
  Categories: agentic-threats
- [llmsec-2026-00366] PromptStudio: A Governance-Aware Agentic AI Framework for Automated Prompt Generation, Optimization, Evaluation, and Lifecycle Management
  https://doi.org/10.22214/ijraset.2026.84092
  Categories: agentic-threats
- [llmsec-2026-00367] Auto-Devops GPT: An Agentic AI Framework for Self-Healing CI/CD Pipelines Using LLM-Based Root Cause Analysis and Reinforcement Learning
  https://doi.org/10.22214/ijraset.2026.84056
  Categories: agentic-threats
- [llmsec-2026-00368] CIVIL AND CRIMINAL LIABILITY OF DEEPFAKE AI PLATFORM PROVIDERS IN VIOLATIONS OF THE RIGHT TO REPUTATION
  https://doi.org/10.71131/0rqvry57
  Categories: social-engineering

Generated by the weekly paper fetch workflow (run #17, trigger: schedule).

auto: add new papers from weekly fetch

d346c8a

github-actions Bot added auto-fetch new-resource labels Jul 19, 2026

github-actions Bot assigned emmanuelgjr Jul 19, 2026

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

auto: new LLM security papers (run #17) - #48

auto: new LLM security papers (run #17)#48
github-actions[bot] wants to merge 1 commit into
mainfrom
auto/papers-17

github-actions Bot commented Jul 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant