Paper Library

Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Indranil Halder, Annesya Banerjee, Cengiz Pehlevan

2026-03-11

red teaming

2603.11331v1

Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models

Xiangwen Wang, Ananth Balashankar, Varun Chandrasekaran

2026-03-11

red teaming

2603.11149v1

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference

Zixun Xiong, Gaoyi Wu, Lingfeng Yao, Miao Pan, Xiaojiang Du, Hao Wang

2026-03-11

red teaming

2603.11132v1

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

Fabrizio Dimino, Bhaskarjit Sarmah, Stefano Pasquali

2026-03-11

red teaming

2603.10807v1

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations

Yu He, Haozhe Zhu, Yiming Li, Shuo Shao, Hongwei Yao, Zhihao Liu, Zhan Qin

2026-03-11

red teaming

2603.10749v1

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu, Christopher A. Choquette-Choo, Steph Lin, Nikhil Kandpal, Milad Nasr, Rai, Sam Toyer, Miles Wang, Yaodong Yu, Alex Beutel, Kai Xiao

2026-03-11

red teaming

2603.10521v1

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities

Nanzi Yang, Weiheng Bai, Kangjie Lu

2026-03-10

red teaming

2603.10163v1

Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference

Fan Yang

2026-03-10

red teaming safety

2603.10091v1

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models

Quanchen Zou, Moyang Chen, Zonghao Ying, Wenzhuo Xu, Yisong Xiao, Deyue Zhang, Dongdong Yang, Zhao Liu, Xiangzheng Zhang

2026-03-10

red teaming

2603.09246v1

Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety

Trent R Northen, Mingxun Wang

2026-03-10

safety

2603.09154v1

ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models

Harry Owiredu-Ashley

2026-03-10

red teaming

2603.10068v1

The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs

Yonghong Deng, Zhen Yang, Ping Jian, Xinyue Zhang, Zhongbin Guo, Chengzhi Li

2026-03-09

red teaming

2603.08234v1

Invisible Safety Threat: Malicious Finetuning for LLM via Steganography

Guangnian Wan, Xinyin Ma, Gongfan Fang, Xinchao Wang

2026-03-09

safety

2603.08104v1

March 09 - March 15, 2026

Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models

WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities

Multi-Stream Perturbation Attack: Breaking Safety Alignment of Thinking LLMs Through Concurrent Task Interference

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models

Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety

ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models

The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs

Invisible Safety Threat: Malicious Finetuning for LLM via Steganography

March 02 - March 08, 2026

DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation

VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription

Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints

Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice

Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice

Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It

Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models

Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads

Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems

Efficient Refusal Ablation in LLM through Optimal Transport