AI Threat Alert
STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
As LLMs advance into autonomous agents with tool-use capabilities
An Automated Framework for Strategy Discovery, Retrieval, and Evolution in LLM Jailbreak Attacks
The widespread deployment of Large Language Models (LLMs) as public
Automating Deception: Scalable Multi-Turn LLM Jailbreaks
paper introduces a novel, automated pipeline for generating large-scale, psychologically-grounded multi-turn jailbreak datasets. We systematically operationalize FITD techniques into reproducible templates, creating a benchmark
Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments
jailbreak smaller ones - eliciting harmful or restricted behavior despite alignment safeguards. Using standardized adversarial tasks from JailbreakBench, we simulate over 6,000 multi-turn attacker-target exchanges across major LLM
TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations
high-value industries continues to expand, the systematic assessment of their safety against jailbreak and prompt-based attacks remains insufficient. Existing safety evaluation benchmarks and frameworks are often limited
LLM Reinforcement in Context
adversarial attacks and misbehavior by training on examples and prompting. Research has shown that LLM jailbreak probability increases with the size of the user input or conversation length. There
Exploiting Latent Space Discontinuities for Building Universal LLM Jailbreaks and Data Extraction Attacks
The rapid proliferation of Large Language Models (LLMs) has raised
AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research
hindering meaningful progress. To address these issues, we introduce AdversariaLLM, a toolbox for conducting LLM jailbreak robustness research. Its design centers on reproducibility, correctness, and extensibility. The framework implements twelve
Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
self-audit: they are able to identify harmful prompts and describe how a safe LLM should respond, yet they comply with the harmful request. With RLVR, harmful behavior is strongly
Stress Testing Concept Erasure with Large Language Model Agents
STACE can be adapted beyond concept erasure evaluation to other problem domains, such as LLM jailbreaking. Our code is available anonymously
The Echo Chamber Multi-Turn LLM Jailbreak
The availability of Large Language Models (LLMs) has led to
ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected
author can inject hidden prompts inside a PDF that secretly guide or "jailbreak" LLM reviewers into giving overly positive feedback and biased acceptance. On the defense side, we propose
AlignTree: Efficient Defense Against LLM Jailbreak Attacks
Large Language Models (LLMs) are vulnerable to adversarial attacks that
SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings
grid-searched traditional SS while eliminating systematic over-counting. We then study PAIR-style LLM jailbreaks under a fleet-level threat model with adversarial fraction $η$. On Llama-Guard
Performative Scenario Optimization
demonstrated through an emerging AI safety application: deploying performative guardrails against Large Language Model (LLM) jailbreaks. Numerical results confirm the co-evolution and convergence of the guardrail classifier
RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs
baselines. These findings highlight the importance of embedding-space regularization for understanding and mitigating LLM jailbreak vulnerabilities
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for Database Bypass
ingest to regenerate operator-specific table reading components without human-engineered parsing logic. Jailbreak leverages LLM-assisted code synthesis for database storage decoding, turning a traditionally opaque format into
Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World
Finally, we demonstrate that such indices can be used to ensure previously inaccessible jailbreak-agnostic LLM safety. We hope that our findings will be useful to other teams attempting large
Consistency Training Helps Stop Sycophancy and Jailbreaks
LLM's factuality and refusal training can be compromised by simple changes to a prompt. Models often adopt user beliefs (sycophancy) or satisfy inappropriate requests which are wrapped within special
Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks
effective attacks. We therefore introduce an adversarial student agent that we fine-tune to jailbreak LLM-based tutors, which we propose as the core of a standardized benchmark for evaluating