← Back to all news
arXiv Machine Learning By Shiliang Xiao

TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization

Read the original on arXiv Machine Learning →

The paper introduces TACS, a trajectory‑aware candidate selection framework designed to improve jailbreak suffix optimization for large language models. Traditional gradient‑based methods choose candidates based solely on the lowest current loss, which the authors argue is myopic and can lead to reward hacking. TACS augments per‑step evaluation with a trajectory‑aware proxy, reference‑policy regularization, and a chi‑squared correction to encourage selections that remain effective beyond the immediate step. Experiments on HarmBench show that TACS consistently outperforms strong baselines, achieving higher attack success rates and more stable optimization behavior.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jun 11

JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

arXiv:2606. 11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off: hand-crafted prompts are expressive but static, while iterative prompt optimization can adapt but often relies on low-level mutations that require many target queries.

By Ge Shi, Jun Yin, Donglin Xie, Fangyi Liu, Yucan Li, Menglin Liu
llmsreinforcement-learningmultimodalsafety
More like this →
arXiv AI
Aug 20

Jailbreaking in the Haystack

The paper "Jailbreaking in the Haystack" introduces NINJA, a jailbreak technique that exploits long-context language models by appending benign, model-generated content to harmful user goals. It demonstrates that the position of harmful goals within the context is crucial for safety, and shows that NINJA significantly boosts attack success rates on models such as LLaMA, Qwen, Mistral, and Gemini. Unlike previous methods, NINJA is low-resource, transferable, less detectable, and compute‑optimal, revealing that carefully crafted benign long contexts can expose fundamental vulnerabilities in modern LMs.

By Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena, Ziqian Zhong, Alexander Robey, Aditi Raghunathan
llmsagentsbenchmarkssafety
More like this →
arXiv AI
Aug 6

Dynamic Jailbreaking Attack

arXiv:2510. 02422v4 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suffix toward a predefined target response with a static optimization strategy.

By Kedong Xiu, Yunhan Yang, Churui Zeng, Tianhang Zheng, Xinzhe Huang, Di Wang, Puning Zhao, Zhan Qin, Kui Ren
llmsmultimodalsafety
More like this →