The paper introduces TrustMI, a method to causally control how large language model assistants decide to trust their users. By creating 2,000 contrastive conversations that vary in ability, benevolence, and integrity, the authors learn steering matrices that adjust trust decisions along linear directions in model activations while keeping the model parameters frozen. Experiments across six instruction‑tuned models show that these steering changes reliably alter trust decisions and affect safety‑related behaviors such as compliance with harmful requests, prompt injections, and insider threats.
arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabi...
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 "cunning questions"—non‑safety prompts that contain misleading premises or subtle inconsistencies—to train large language models (LLMs) to scrutinize underlying intent and assumptions. Experiments show that incorporating these questions improves robustness against out‑of‑distribution jailbreak attacks and enhances subsequent safety fine‑tuning, achieving a new state‑of‑the‑art reduction in mean ASR from 17.40% to 15.05% across nine backbone–benchmark combinations. The authors argue that this training fosters vigilance, enabling models to prioritize safety judgments before engaging in harmful planning.
arXiv:2606. 00566v1 Announce Type: new Abstract: As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party content, their attack surface expands well beyond what users type.
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.
arXiv:2606. 05614v1 Announce Type: new Abstract: 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.
arXiv:2606. 08044v1 Announce Type: cross Abstract: Large Language Model (LLM) safety has often been evaluated at the behavior level, which provides limited evidence of internal robustness, as these evaluations target outputs rather than representation-level vulnerability under intervention.
arXiv:2605.12015v3 Announce Type: replace-cross Abstract: Reusable skills are becoming a common interface for extending large language model agents, packaging procedural guidance with access to files...
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.
ADeptS-Bench is a new benchmark designed to assess the trustworthiness of Computer Use Agents (CUAs) across mobile and desktop devices. It consists of two streams: a Safety stream with paired benign and malicious tasks that embed visual threats, and a Disambiguation stream that tests whether agents seek clarification when instructions are ambiguous. Evaluation of seven models shows none consistently achieves high task success while keeping attack success low, and all models exhibit problematic behaviors such as unhesitant checkout on a $25K order and failure to detect a mislabeled factory reset button.
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.
arXiv:2606. 26106v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in emotionally charged situations involving interpersonal conflict, frustration, and distress.