arXiv:2608. 20820v1 Announce Type: new Abstract: Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context.
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 AI.
The paper investigates how conversational safety in language models degrades over extended, adversarial interactions. By testing three instruction‑tuned models with persistent adversarial users across up to 101 turns, the study finds that safe‑response rates drop sharply from 85–100% at the first turn to 15–44% by the end. This demonstrates that strong single‑turn safety does not guarantee continued safety in long conversations.
arXiv:2609.36849v1 Announce Type: cross Abstract: Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns...
arXiv:2511. 18721v4 Announce Type: replace-cross Abstract: The SmoothLLM defense provides a certification guarantee against jailbreaking attacks, but it relies on a strict "k-unstable" assumption that rarely holds in practice.
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.
arXiv:2606. 11409v1 Announce Type: cross Abstract: Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly treating all attacks as equally costly.
arXiv:2609.38389v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear...