Related papers: Measuring AI Agents' Progress on Multi-Step Cyber …
Advanced Persistent Threats (APTs) represent a sophisticated and persistent cy-bersecurity challenge, characterized by stealthy, multi-phase, and targeted attacks aimed at compromising information systems over an extended period.…
Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user privileges and are distributed through community registries with minimal vetting, but no…
Inference attacks have been widely studied and offer a systematic risk assessment of ML services; however, their implementation and the attack parameters for optimal estimation are challenging for non-experts. The emergence of advanced…
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…
Recent advances in AI are transforming AI's ubiquitous presence in our world from that of standalone AI-applications into deeply integrated AI-agents. These changes have been driven by agents' increasing capability to autonomously make…
Evidence on AI in software engineering still leans heavily toward individual task completion, while evidence on team-level delivery remains scarce. We report a retrospective longitudinal field study of Chiron, an industrial platform that…
Training advanced AI models requires large investments in computational resources, or compute. Yet, as hardware innovation reduces the price of compute and algorithmic advances make its use more efficient, the cost of training an AI model…
AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make…
Advanced Persistent Threats (APTs) evolve through multiple stages, each exhibiting distinct temporal and structural behaviors. Accurate stage estimation is critical for enabling adaptive cyber defense. This paper presents StageFinder, a…
Cybercriminals are rapidly developing new malicious tools that leverage artificial intelligence (AI) to enable new classes of adaptive and stealthy attacks. New defensive methods need to be developed to counter these threats. Some…
Cyber Threat Intelligence (CTI) plays a crucial role in assessing risks and enhancing security for organizations. However, the process of extracting relevant information from unstructured text sources can be expensive and time-consuming.…
Recent progress in AI capabilities has heightened concerns that AI systems could pose a threat to national security, for example, by making it easier for malicious actors to perform cyberattacks on critical national infrastructure, or…
METR's time horizon metric has grown exponentially since 2019, along with compute. However, it is unclear whether compute scaling will persist at current rates through 2030, raising the question of how possible compute slowdowns might…
Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even…
Frontier AI companies first deploy their most advanced models internally, for weeks or months of safety testing, evaluation, and iteration, before a possible public release. For example, Anthropic recently developed a new class of model…
Artificial intelligence systems are now deployed at scale across sectors, accompanied by a growing number of real-world incidents ranging from misinformation and cybercrime to autonomous-system failures. Databases of AI incidents index…
AI agents execute complex multi-step processes, but current evaluation falls short: outcome metrics report success or failure without explaining why, and process-level approaches struggle to connect failure types to their precise locations…
We evaluate artificial intelligence (AI) systems without ground truth by exploiting a link between strategic gaming and information loss. Building on established information theory, we analyze which mechanisms resist adversarial…
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…
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…