Paper Library

SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement

Xiaojun Jia, Jie Liao, Simeng Qin, Jindong Gu, Wenqi Ren, Xiaochun Cao, Yang Liu, Philip Torr

2026-02-15

red teaming

2602.14211v1

When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift

Max Fomin

2026-02-15

red teaming

2602.14161v1

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

Yuqi Jia, Ruiqi Wang, Xilong Wang, Chong Xiang, Neil Gong

2026-02-14

red teaming

2602.13597v2

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

Yuqi Jia, Ruiqi Wang, Xilong Wang, Chong Xiang, Neil Gong

2026-02-14

red teaming

2602.13597v1

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

Yanbo Wang, Minzheng Wang, Jian Liang, Lu Wang, Yongcan Yu, Ran He

2026-02-14

safety

2602.13562v1

AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks

Weiming Song, Xuan Xie, Ruiping Yin

2026-02-14

2602.13547v1

OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage

Akshat Naik, Jay Culligan, Yarin Gal, Philip Torr, Rahaf Aljundi, Alasdair Paren, Adel Bibi

2026-02-13

red teaming

2602.13477v2

OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage

Akshat Naik, Jay Culligan, Yarin Gal, Philip Torr, Rahaf Aljundi, Alasdair Paren, Adel Bibi

2026-02-13

red teaming

2602.13477v1

Buy versus Build an LLM: A Decision Framework for Governments

Jiahao Lu, Ziwei Xu, William Tjhi, Junnan Li, Antoine Bosselut, Pang Wei Koh, Mohan Kankanhalli

2026-02-13

governance

2602.13033v1

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

Yannick Assogba, Jacopo Cortellazzi, Javier Abad, Pau Rodriguez, Xavier Suau, Arno Blaas

2026-02-12

red teaming

2602.12418v1

Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing

Keita Broadwater

2026-02-12

safety

2602.11786v1

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs

Dong Yan, Jian Liang, Ran He, Tieniu Tan

2026-02-12

safety

2602.11528v1

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis

2026-02-12

red teaming

2602.11495v1

Towards Reliable Machine Translation: Scaling LLMs for Critical Error Detection and Safety

Muskaan Chopra, Lorenz Sparrenberg, Rafet Sifa

2026-02-11

safety

2602.11444v1

Optimizing Agent Planning for Security and Autonomy

Aashish Kolluri, Rishi Sharma, Manuel Costa, Boris Köpf, Tobias Nießen, Mark Russinovich, Shruti Tople, Santiago Zanella-Béguelin

2026-02-11

2602.11416v1

February 16 - February 22, 2026

Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

The Vulnerability of LLM Rankers to Prompt Injection Attacks

Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis

Intent Laundering: AI Safety Datasets Are Not What They Seem

Boundary Point Jailbreaking of Black-Box LLMs

Boundary Point Jailbreaking of Black-Box LLMs

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks

Multi-Turn Adaptive Prompting Attack on Large Vision-Language Models

A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)

February 09 - February 15, 2026

SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement

When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning

AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks

OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage

OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage

Buy versus Build an LLM: A Decision Framework for Governments

Sparse Autoencoders are Capable LLM Jailbreak Mitigators

Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs

Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models

Towards Reliable Machine Translation: Scaling LLMs for Critical Error Detection and Safety

Optimizing Agent Planning for Security and Autonomy