相关论文: Comparing AI Agents to Cybersecurity Professionals…
AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecurity. Current red-teaming tools often rely on fixed benchmarks…
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…
AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this…
This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark contains curated end-to-end tasks (e.g.,…
Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks, while human auditors are thorough but slow…
Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…
The integration of large language models (LLMs) into healthcare IoT systems promises faster decisions and improved medical support. LLMs are also deployed as multi-agent teams to assist AI doctors by debating, voting, or advising on…
We explore the potential for productive team-based collaboration between humans and Artificial Intelligence (AI) by presenting and conducting initial tests with a general framework that enables multiple human and AI agents to work together…
Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…
In programming education, plagiarism and misuse of artificial intelligence (AI) assistance are emerging issues. However, not many relevant studies are focused on web programming. We plan to develop automated tools to help instructors…
As artificial intelligence (AI) becomes deeply embedded in critical services and everyday products, it is increasingly exposed to security threats which traditional cyber defenses were not designed to handle. In this paper, we investigate…
Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…
Can artificial intelligence truly contribute to creative mathematical research, or does it merely automate routine calculations while introducing risks of error? We provide empirical evidence through a detailed case study: the discovery of…
In the network security arms race, the defender is significantly disadvantaged as they need to successfully detect and counter every malicious attack. In contrast, the attacker needs to succeed only once. To level the playing field, we…
Advances in AI are widely understood to have implications for cybersecurity. Articles have emphasized the effect of AI on the cyber offense-defense balance, and commentators can be found arguing either that cyber will privilege attackers or…
Artificial intelligence (AI) agents are emerging as transformative tools in drug discovery, with the ability to autonomously reason, act, and learn through complicated research workflows. Building on large language models (LLMs) coupled…
Commercial insurance underwriting is a labor-intensive process that requires manual review of extensive documentation to assess risk and determine policy pricing. While AI offers substantial efficiency improvements, existing solutions lack…
In order for agents trained by deep reinforcement learning to work alongside humans in realistic settings, we will need to ensure that the agents are \emph{robust}. Since the real world is very diverse, and human behavior often changes in…
BGP prefix hijacking is a critical threat to Internet organizations and users. Despite the availability of several defense approaches (ranging from RPKI to popular third-party services), none of them solves the problem adequately in…
We model a competitive market where AI agents buy answers from upstream generative models and resell them to users who differ in how much they value accuracy and in how much they fear hallucinations. Agents can privately exert effort for…