Search: “red-teaming”

arXiv:2610.00960v1 Announce Type: new Abstract: A video benchmark should reward the capability it claims to measure, yet models can exploit answer options, question text, or partial visual evidence. W

arXiv:2609.38971v1 Announce Type: cross Abstract: Embodied vision-language models (VLMs) are increasingly deployed as high-level planners for robots because they generalize across diverse environments

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 h

arXiv:2609.40027v1 Announce Type: new Abstract: Causal action verifiers gate an agent's state-changing tool calls by checking whether each proposed intervention is identifiable against a committed act

arXiv:2609.36570v1 Announce Type: cross Abstract: Indirect prompt injection makes an LLM agent treat untrusted retrieved text as instructions. We present CounterSteer, an inference-time defense that s

arXiv:2412.16633v4 Announce Type: replace Abstract: LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), a

arXiv:2505.14368v3 Announce Type: replace-cross Abstract: Recent studies demonstrate that Large Language Models (LLMs) are vulnerable to attacks that generate harmful or sensitive outputs. As open-sou

arXiv:2609.30383v1 Announce Type: new Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend i

Every week, I talk with founders who are building at an unbelievable pace. Teams are moving from inception to product-market fit faster than ever, with foundation models wired deeply into their core p

arXiv:2609.23894v1 Announce Type: cross Abstract: Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other age

arXiv:2312.06632v2 Announce Type: replace Abstract: Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful substa

arXiv:2609.19101v1 Announce Type: new Abstract: As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model represent

arXiv:2607.18063v2 Announce Type: replace-cross Abstract: LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. We present a 21-scenario benchmark f

New York Times: Democrats and Republicans proposed many bills to address major AI threats over the past two years, but they remain stymied by partisan disputes and lobbying — For years, Democrats and

arXiv:2609.15422v1 Announce Type: new Abstract: AI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes a

arXiv:2609.15134v1 Announce Type: new Abstract: Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through ru

arXiv:2609.14861v1 Announce Type: cross Abstract: A deployed language model may refuse a harmful request in English yet comply with its faithful translation, revealing a cross-lingual safety failure t

arXiv:2606.23189v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-appli

arXiv:2606.16000v3 Announce Type: replace Abstract: We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agen

arXiv:2609.09404v1 Announce Type: cross Abstract: Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also read

arXiv:2606.16723v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is

Gian Volpicelli / Bloomberg: Anthropic gives EU cybersecurity agency ENISA testing access to Mythos 5 after months of talks that began in late May; ENISA still lacks access to Mythos 5.1 — Anthropic P

arXiv:2609.10036v1 Announce Type: cross Abstract: Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment be

arXiv:2609.06391v1 Announce Type: new Abstract: Graph-agentic retrieval-augmented generation combines structured evidence with adaptive controllers that can plan retrieval, traverse relations, verify

arXiv:2609.09396v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) advance toward physical deployment, the focus has remained on action-oriented Embodied AI evaluated on subject-centric

arXiv:2609.07529v1 Announce Type: new Abstract: Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions in

arXiv:2609.06058v1 Announce Type: new Abstract: As vision-language models (VLMs) become increasingly capable and are deployed in consequential real-world settings, they must evaluate evidence independ

arXiv:2609.02902v1 Announce Type: new Abstract: Deploying task-oriented dialogue agents in enterprise customer support faces a persistent annotation bottleneck: robust training requires labelled inter

arXiv:2609.04159v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale:

arXiv:2609.03955v1 Announce Type: new Abstract: Reinforcement learning (RL) has substantially advanced code generation with large language models (LLMs) through executable feedback. The feedback for c

Artificial intelligence security startup HiddenLayer Inc. today announced a 100 million Series B round, and a separate 27 million Series A went to edge security company Huskeys Security Ltd. Austin-ba

arXiv:2609.01691v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to make decisions from visual inputs. We introduce FAIRLENS, a benchmark and evaluation framework fo

arXiv:2609.02786v1 Announce Type: new Abstract: The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to

arXiv:2609.00384v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly automate multi-step engineering workflows through tool use, interpretation of intermediate results, and i

arXiv:2607.15550v2 Announce Type: replace Abstract: Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safe

arXiv:2608.30986v1 Announce Type: cross Abstract: Activation steering has emerged as a lightweight approach for controlling model refusal at inference time. A growing line of research explores trainab

arXiv:2603.22978v2 Announce Type: replace Abstract: In the maintenance of complex systems, fault trees are used to locate problems and provide targeted solutions. To enable fault trees stored as image

arXiv:2603.02482v2 Announce Type: replace-cross Abstract: Safety evaluation of multimodal large language models requires tracking not only whether an attack succeeds, but also how the interaction unfo

arXiv:2608.30041v1 Announce Type: cross Abstract: Large language model agents place outputs from external skills into their execution context, allowing attacker-controlled data to influence later priv

arXiv:2608.28593v1 Announce Type: new Abstract: With the increasing development of AI regulatory frameworks, ensuring that artificial intelligence systems, particularly generative models, operate in a

arXiv:2606.17092v2 Announce Type: replace-cross Abstract: Agentic systems are increasingly integrated with geographic information systems (GIS), where multi-agent coordination enables complex conversa

arXiv:2608.27021v1 Announce Type: cross Abstract: LLM-based agents are increasingly proposed for network fault diagnosis, but existing benchmarks evaluate them only on accurate tickets and always assu

arXiv:2606.12984v2 Announce Type: replace Abstract: Image-based AI assistants are now deployed at production scale on e-commerce platforms, where a single uploaded image can trigger fundamentally diff

arXiv:2608.26008v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques such as role-playing, obfuscation, code transformation, an

arXiv:2608.23663v1 Announce Type: cross Abstract: Aligning deployed language models requires knowing when their outputs can be trusted, yet on-device models now ship to hundreds of millions of devices

arXiv:2608.21423v1 Announce Type: cross Abstract: Agentic security uses large-language-model (LLM) agents to plan, dispatch, and interpret security tools. As these systems move from demonstrations to