Related papers: StepShield: When, Not Whether to Intervene on Rogu…
Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…
Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…
The rapid deployment of Large language model (LLM) agents in critical domains like healthcare and finance necessitates robust security frameworks. To address the absence of standardized evaluation benchmarks for these agents in dynamic…
Advancing safe autonomous systems through reinforcement learning (RL) requires robust benchmarks to evaluate performance, analyze methods, and assess agent competencies. Humans primarily rely on embodied visual perception to safely navigate…
Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity…
Recent advances in AI-assisted programming have empowered agents to execute complex workflows via command-line interfaces, however, existing benchmarks are limited by short task horizons, data contamination from GitHub scraping, and a lack…
Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…
Intrusion Detection and Prevention Systems (IDS/IPS) in large enterprises can generate hundreds of thousands of alerts per hour, overwhelming analysts with logs requiring rapidly evolving expertise. Conventional machine-learning detectors…
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous…
AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspired by the well-established concept of firewalls, we show…
Intrusion Detection Systems (IDS) are critical to defending enterprise and industrial control environments, yet evaluating their effectiveness under realistic conditions remains an open challenge. Existing benchmarks rely on synthetic…
Modern distributed systems employ aggressive optimization strategies that create latent risks - hidden vulnerabilities where exceptional performance masks catastrophic fragility when optimizations fail. Cache layers achieving 99% hit rates…
As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests…
Advancements in AI have led to agents in networked environments increasingly mirroring human behavior, thereby blurring the boundary between artificial and human actors in specific contexts. This shift brings about significant challenges in…
The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user objectives, violate data handling policies, or be compromised by…
Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…
The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional…
Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this…
Solving sequential decision prediction problems, including those in imitation learning settings, requires mitigating the problem of covariate shift. The standard approach, DAgger, relies on capturing expert behaviour in all states that the…
With the increasing adoption of large language models (LLM), agentic workflows, which compose multiple LLM calls with tools, retrieval, and reasoning steps, are increasingly replacing traditional applications. However, such workflows are…