arXiv AI
Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 2
THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
arXiv:2606. 01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination.
arXiv AI
Aug 18
TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation
arXiv:2608. 15594v1 Announce Type: new Abstract: Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails.
arXiv AI
Aug 11
Automating Deception: Scalable Multi-Turn LLM Jailbreaks
arXiv:2511. 19517v3 Announce Type: replace-cross Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs).
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.
arXiv AI
Sep 10
SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement
arXiv:2609.05850v1 Announce Type: cross Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reve...
arXiv AI
Jul 14
Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message
arXiv:2507. 04673v2 Announce Type: replace Abstract: The rise of conversational interfaces has greatly enhanced LLM usability by leveraging dialogue history for sophisticated reasoning.