The paper introduces a counterfactually anchored evidence attribution approach for multi‑turn large language model safety failures. It presents a new dataset of 1,762 conversations, including adversarial, benign twins, and high‑risk vocabulary variants, and trains a lightweight hierarchical model that accurately predicts safety violations and attributes them to specific user turns and token spans. The model achieves high detection performance (F1 = 0.988) and significantly reduces adversarial confidence when top‑attributed tokens are removed, while maintaining low false‑positive rates on benign conversations.
arXiv:2607. 19361v1 Announce Type: cross Abstract: Most safety guardrails for large language models (LLMs) evaluate each prompt-response pair in isolation, which misses failures that arise only over a dialogue as benign turns compose into harm.
arXiv:2606. 25476v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes applications raises critical concerns regarding reliability, safety, and trustworthiness.
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
arXiv:2609.13579v1 Announce Type: new Abstract: Safety research often focuses on model-generated harms, but users may also direct hostility, coercion, and adversarial pressure at models. Understandin...
The paper introduces CarryOnBench, an interactive benchmark that tests whether large language models can revise their interpretation of user intent and recover utility while staying safe in multi‑turn conversations. Using 398 harmful‑looking queries with benign intents, the benchmark simulates 5,970 conversations across 14 models, evaluating both intent‑aligned utility and safety with a new metric called Ben‑Util. Results show that models often withhold information due to misinterpretation, but most can recover with clarifications, revealing failure modes such as unsafe and redundant recovery that single‑turn tests miss.
arXiv:2607. 20472v1 Announce Type: new Abstract: When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question?
arXiv:2606. 02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their capabilities through extended interactions.
The paper introduces the SAST-IR framework to evaluate large language models’ robustness against persuasion attacks in a memory‑less setting, revealing a flaw called "Refusal Inertia" that masks true vulnerability. Using the CP‑Agent and a custom CounterFact‑Strict dataset, the authors demonstrate that simple, diverse attack strategies achieve a 96% success rate, while complex attacks often trigger defensive compliance. The study highlights severe brittleness in current state‑of‑the‑art models when deprived of conversation history.
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:2608.21775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in real-world applications, yet they remain vulnerable to generating harmful content. From adver...
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
The paper introduces MINT‑Safe, a new open‑source dataset of 11,270 multi‑image dialogues and 500 refusal VQA pairs designed to expose safety risks in multi‑modal large language models during open‑ended conversations. It also proposes TAD‑Align, a turn‑aware dual‑objective reward framework that dynamically up‑weights dialogue turns with inconsistent safety behavior, improving safety metrics on Qwen2.5‑VL‑7B‑Instruct and LLaVA‑Next‑7B. The results show over 10% reduction in attack success rate and notable gains in harmlessness and helpfulness while maintaining overall model performance.