AI Threat AlertEchoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks
Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn
On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
Aligned models can misbehave in several ways: they are often
Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents
LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky or negative personas. Most prior work
Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models
ensemble of 3 open-weight LLM judges, whose binary safety assessments were validated on a stratified human-labeled subset. Poetic framing achieved an average jailbreak success rate
Don't Walk the Line: Boundary Guidance for Filtered Generation
margin. On a benchmark of jailbreak, ambiguous, and longcontext prompts, Boundary Guidance improves both the safety and the utility of outputs, as judged by LLM-as-a-Judge evaluations. Comprehensive
Stop Testing Attacks, Start Diagnosing Defenses: The Four-Checkpoint Framework Reveals Where LLM Safety Breaks
existing research demonstrates that jailbreak attacks succeed, it does not explain \textit{where} defenses fail or \textit{why}. To address this gap, we propose that LLM safety operates
Distillability of LLM Security Logic: Predicting Attack Success Rate of Outline Filling Attack via Ranking Regression
realm of black-box jailbreak attacks on large language models (LLMs), the feasibility of constructing a narrow safety proxy, a lightweight model designed to predict the attack success rate
Extracting books from production language models
recall). With different per-LLM experimental configurations, we were able to extract varying amounts of text. For the Phase 1 probe, it was unnecessary to jailbreak Gemini
PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations
privacy risk in active LLM contexts should be evaluated as a persistent behavioral failure mode rather than only as training-data memorization or immediate jailbreak behavior
RAS: Measuring LLM Safety Through Refusal Alignment
measuring whether its hidden states align with these refusal directions under unsafe and jailbreak prompts. The resulting metric, **RAS** (**R**efusal **A**lignment **S**core), maps representation-level refusal alignment
Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
test time, showing LLM reasoning improves satisfaction of model specifications designed to thwart attacks, resulting in a correlation between reasoning effort and robustness to jailbreaks. However, this benefit of test
Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
risk of unpredictable LLM behavior. In addition, this two-stage scheme offers a distinct advantage in striking a balance between harmlessness and helpfulness in jailbreaking defense. Notably, we present
Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models
canonical jailbreak strategies. Second, when compromised, LLMs frequently generate actionable yet harmful instructions, inadvertently empowering malicious actors and posing tangible risks. Third, existing LLM-based guardrails systematically overlook these domain
Is It Possible to Make Chatbots Virtuous? Investigating a Virtue-Based Design Methodology Applied to LLMs
vulnerable to jailbreaking, were generalizing models too widely, and had potential implementation issues. Overall, participants reacted positively while also acknowledging the tradeoffs involved in ethical LLM design
Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming
vulnerability rules, through LLM-driven agentic auditing of MCP servers and agent-skill packages and multi-turn black-box agent red teaming, to a jailbreak harness with 26+ attack operators
GSAE: Graph-Regularized Sparse Autoencoders for Robust LLM Safety Steering
Large language models (LLMs) face critical safety challenges, as they
AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and adversarial collaboration. Existing
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
weight models, 22 jailbreak attack types, and a benchmark of short, single-turn benign questions, comparing against three representative prompt-level baselines (Llama Guard, RA-LLM, Goal Prioritization). Among
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
Safety alignment in large language models (LLMs) remains brittle against
Efficient Refusal Ablation in LLM through Optimal Transport
Safety-aligned language models refuse harmful requests through learned refusal