arXiv Machine Learning October 5, 2026 By Fengwei Tian, Ravi Tandon

Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional Attacks

Read the original on arXiv Machine Learning →

The paper introduces an information‑theoretic framework for studying intent‑hiding jailbreaks against large language models. It defines prior‑posterior matching, where auxiliary tasks are chosen so that the average probability of harmful intent in a bundle matches the overall prior, thereby concealing a harmful target. The authors analyze both query‑independent and query‑dependent settings, proving computational hardness for exact matching, deriving a water‑filling solution for fractional weights, and evaluating the trade‑off between bundle size and target preservation across several open‑source models.

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.

arXiv Machine Learning

Sep 3

Context Inference Attacks Without Jailbreaks

The paper investigates privacy risks in agentic AI systems that assemble sensitive data into a hidden context before responding. It introduces context‑inference attacks, a security game that evaluates how well attackers can recover this hidden context under varying levels of knowledge and indirect delivery. Experiments show that even with controls such as instructions not to disclose, logit suppression, and context dilution, agents can leak significant contextual information, achieving high success rates across multiple attack settings.

By Prince Jha, Samuele Poppi, Nils Lukas

agents multimodal safety

arXiv AI

Sep 10

SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure

arXiv:2609.06540v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in safety-critical applications, yet jailbreak attacks can conceal harmful intent through role...

By Qi Wang, Chengcheng Wan, Jiangtao Wang

llms benchmarks safety

arXiv AI

Sep 7

AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks

AlcaTRAz is a prompt‑level defense that uses rule trees to insert controlled character‑level perturbations into input text, disrupting jailbreak attacks without modifying or retraining the target LLM. It operates solely on the input, making it suitable for black‑box deployments, and was evaluated on 33 open‑weight models and 22 jailbreak types, outperforming three baseline defenses in 73.4 % of model‑attack combinations. While it significantly reduces high‑severity jailbreak success, it does not eliminate it and is intended as one layer of a broader defense strategy.

By Jakub Re\v{s}, Petr Ka\v{s}ka, Martin Pere\v{s}\'ini, Martin Ukrop, Kamil Malinka

llms benchmarks safety

arXiv Computation and Language

Sep 22

BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning

arXiv:2605.27110v2 Announce Type: replace-cross Abstract: In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that elicits malicious information through in...

By Xuan Luo, Yue Wang, Geng Tu, Jing Li, Ruifeng Xu

llms safety

arXiv AI

Jul 20

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.

By Wenpeng Xing, Bohan Yang, Mohan Li, Chunqiang Hu, Haitao Xu, Ningyu Zhang, Bo Lin, Meng Han

llms multimodal benchmarks safety

arXiv AI

Jun 3

D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting

arXiv:2606. 02640v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they exploit feedback from auxiliary judge models to iteratively refine prompts toward harmful goals.

By Huanli Gong, Zhipeng Wei, Yu Fu, Haz Sameen Shahgir, Ananya Gupta, Yue Dong, N. Benjamin Erichson

llms fine-tuning benchmarks safety

One email a morning, machine-written

Related stories

Context Inference Attacks Without Jailbreaks

SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure

AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks

BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting