The paper investigates a continuation-triggered jailbreak in large language models, showing that moving an instruction suffix can markedly boost jailbreak success. By performing mechanistic interpretability at the attention‑head level, the authors reveal that the jailbreak arises from a competition between the model’s natural continuation drive and safety defenses learned during alignment. They introduce Head Competition Steering (HCS), an inference‑time technique that exploits this competition to suppress harmful outputs and distill the approach into a student model for efficient safety improvements.
arXiv:2607. 00572v1 Announce Type: new Abstract: Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks succeed and informs the design of robust alignment strategies.
arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.
arXiv:2606. 28153v1 Announce Type: cross Abstract: Jailbreak attacks bypass LLM safety alignment, yet their mechanisms remain poorly understood.
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
arXiv:2607. 20473v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly released as open-weight models with safeguards against harmful requests.
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: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).
Safety evaluation is critical for assessing whether aligned Large Language Models (LLMs) remain robust against jailbreak attacks. Existing automated testing methods, however, largely rely on response-...
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.
arXiv:2606. 25182v1 Announce Type: cross Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training.
NeuronFuzz is a white‑box fuzzing framework that uses internal safety neurons of large language models as continuous feedback for safety evaluation, eliminating the need to generate full model responses during testing. It constructs a SafetyOracle that converts neuron activations into a differentiable safety alarm score, enabling gradient‑based identification of sensitive template positions and fluent, context‑compatible prompt mutations. Evaluated on 21 text and multimodal models, NeuronFuzz achieves a 76‑100% jailbreak discovery rate on five white‑box source models and demonstrates strong zero‑shot transfer to open‑weight and proprietary targets.
arXiv:2607. 07903v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit remarkable capabilities but remain highly vulnerable to adversarial prompts and jailbreak attacks.