Related papers: Measuring AI Agents' Progress on Multi-Step Cyber …

Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on…

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…

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…

AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human…

To understand and predict the societal impacts of highly autonomous AI systems, we need benchmarks with grounding, i.e., metrics that directly connect AI performance to real-world effects we care about. We present HCAST (Human-Calibrated…

Agent Skills, structured packages of procedural knowledge loaded into an LLM agent at inference time, are widely reported to improve task pass rates by an average of 16.2~percentage points across diverse domains. Yet the same benchmarks…

Frontier AI models -- highly capable foundation models at the cutting edge of AI development -- may pose severe risks to public safety, human rights, economic stability, and societal value in the coming years. These risks could arise from…

Traditional rule-based cybersecurity systems have proven highly effective against known malware threats. However, they face challenges in detecting novel threats. To address this issue, emerging cybersecurity systems are incorporating AI…

The progress of artificial intelligence (AI) has made sophisticated methods available for cyberattacks and red team activities. These AI attacks can automate the process of penetrating a target or collecting sensitive data. The new methods…

As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…

Cyber threats continue to evolve in complexity, thereby traditional Cyber Threat Intelligence (CTI) methods struggle to keep pace. AI offers a potential solution, automating and enhancing various tasks, from data ingestion to resilience…

Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sample throughput, limiting the benefit of search; (2) a generalization gap where…

Cyber threat intelligence (CTI) encoded in STIX and structured according to the MITRE ATT&CK framework has become a global reference for describing adversary behavior. However, ATT&CK was designed as a descriptive knowledge base rather than…

Existing AI agents typically execute multi-step tasks autonomously and only allow user confirmation at the end. During execution, users have little control, making the confirm-at-end approach brittle: a single error can cascade and force a…

The recent development of powerful AI systems has highlighted the need for robust risk management frameworks in the AI industry. Although companies have begun to implement safety frameworks, current approaches often lack the systematic…

The research creates a professional certification survey to test large language models and evaluate their employable skills. It compares the performance of two AI models, GPT-3 and Turbo-GPT3.5, on a benchmark dataset of 1149 professional…

The use of Artificial Intelligence (AI) and Machine Learning (ML) to solve cybersecurity problems has been gaining traction within industry and academia, in part as a response to widespread malware attacks on critical systems, such as cloud…

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…

Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…

This paper explores the evolving dynamics of cybersecurity in the age of advanced AI, from the perspective of the introduced Human Layer Kill Chain framework. As traditional attack models like Lockheed Martin's Cyber Kill Chain become…