English
Related papers

Related papers: TraceGuard: Structured Multi-Dimensional Monitorin…

200 papers

We introduce WildGuard -- an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal…

Computation and Language · Computer Science 2024-12-11 Seungju Han , Kavel Rao , Allyson Ettinger , Liwei Jiang , Bill Yuchen Lin , Nathan Lambert , Yejin Choi , Nouha Dziri

Modern software systems are increasingly developed within rapid continuous integration and deployment (CI/CD) pipelines, where ensuring security prior to release presents significant technical and organizational challenges. Traditional…

Software Engineering · Computer Science 2026-05-01 Michael Wienczkowski

With a rapid growth in the IT industry, Internet of Things (IoT) has gained a tremendous attention and become a central aspect of our environment. In IoT the things (devices) communicate and exchange the data without the act of human…

Cryptography and Security · Computer Science 2020-01-10 Jawad Ali , Toqeer Ali , Yazed Alsaawy , Ahmad Shahrafidz Khalid , Shahrulniza Musa

As AI agents surpass human capabilities, scalable oversight -- the problem of effectively supplying human feedback to potentially superhuman AI models -- becomes increasingly critical to ensure alignment. While numerous scalable oversight…

Artificial Intelligence · Computer Science 2025-04-08 Abhimanyu Pallavi Sudhir , Jackson Kaunismaa , Arjun Panickssery

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Artificial Intelligence · Computer Science 2026-05-26 Jinhu Qi , Muzhi Li , Jiahong Liu , Yuqin Shu , Dianzhi Yu , Shicheng Ma , Wenqian Cui , Yiyang Zhao , Yiyi Chen , Ruoxi Jiang , Irwin King , Zenglin Xu

Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and…

Artificial Intelligence · Computer Science 2026-05-01 Yu-Chao Huang , Zhen Tan , Mohan Zhang , Pingzhi Li , Zhuo Zhang , Tianlong Chen

Artificial intelligence (AI) agents are increasingly used in a variety of domains to automate tasks, interact with users, and make decisions based on data inputs. Ensuring that AI agents perform only authorized actions and handle inputs…

Cryptography and Security · Computer Science 2026-01-16 Nadya Abaev , Denis Klimov , Gerard Levinov , David Mimran , Yuval Elovici , Asaf Shabtai

We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public…

Artificial Intelligence · Computer Science 2026-01-06 Ron F. Del Rosario

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

Artificial Intelligence · Computer Science 2025-05-12 Markov Grey , Charbel-Raphaël Segerie

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

Artificial Intelligence · Computer Science 2026-05-07 Chenglin Yang

The accelerating adoption of large language models, retrieval-augmented generation pipelines, and multi-agent AI workflows has created a structural governance crisis. Organizations cannot govern what they cannot see, and existing compliance…

We introduce AutoMonitor-Bench, the first benchmark designed to systematically evaluate the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes. AutoMonitor-Bench consists of 3,010 carefully annotated test…

Computation and Language · Computer Science 2026-05-13 Shu Yang , Jingyu Hu , Tong Li , Hanqi Yan , Wenxuan Wang , Di Wang

Existing benchmarks for LLM-based vulnerability detection compress model performance into a single metric, which fails to reflect the distinct priorities of different stakeholders. For example, a CISO may emphasize high recall of critical…

Cryptography and Security · Computer Science 2026-04-03 Subho Halder , Siddharth Saxena , Kashinath Kadaba Shrish , Thiyagarajan M

Various AI safety datasets have been developed to measure LLMs against evolving interpretations of harm. Our evaluation of five recently published open-source safety benchmarks reveals distinct semantic clusters using UMAP dimensionality…

Machine Learning · Computer Science 2025-05-26 Jonathan Bennion , Shaona Ghosh , Mantek Singh , Nouha Dziri

Intrusion detection is a long standing and crucial problem in security. A system capable of detecting intrusions automatically is on great demand in enterprise security solutions. Existing solutions rely heavily on hand-crafted rules…

Cryptography and Security · Computer Science 2024-04-23 Jiongliang Lin , Yiwen Guo , Hao Chen

An attacker can split a malicious goal into sub-prompts that each look benign on their own and only become harmful in combination. Existing LLM safety benchmarks evaluate prompts one at a time, or across turns of a single chat, and so do…

As AI models are deployed with increasing autonomy, it is important to ensure they do not take harmful actions unnoticed. As a potential mitigation, we investigate Chain-of-Thought (CoT) monitoring, wherein a weaker trusted monitor model…

Artificial Intelligence · Computer Science 2025-11-26 Benjamin Arnav , Pablo Bernabeu-Pérez , Nathan Helm-Burger , Tim Kostolansky , Hannes Whittingham , Mary Phuong

Incident monitoring can drive safety improvements in high-reliability industries and population-scale technologies, but remains underdeveloped in AI governance. Public databases catalog thousands of AI incidents, but simple incident counts…

Computers and Society · Computer Science 2026-05-08 Isaak Mengesha , Branwen Owen , Charlie Collins , Tina Wong , Simon Mylius , Peter Slattery , Sean McGregor

Existing agent safety benchmarks report binary accuracy, conflating early intervention with post-mortem analysis. A detector that flags a violation at step 8 enables intervention; one that reports it at step 48 provides only forensic value.…

AI coding scaffolds like Claude Code and Codex use retrying: blocking actions flagged as risky and continuing the trajectory. We study retrying from an AI control perspective, which treats the model as potentially adversarial. We find that…

Artificial Intelligence · Computer Science 2026-05-27 James Lucassen , Adam Kaufman