Related papers: AXE: An Agentic eXploit Engine for Confirming Zero…

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…

Automated code vulnerability detection is critical for software security, yet existing approaches face a fundamental trade-off between detection accuracy and computational cost. We propose a heterogeneous multi-agent architecture inspired…

The increasing deployment of Large Language Model (LLM) agents for complex software engineering tasks has created a need to understand their problem-solving behaviours beyond simple success metrics. While these agents demonstrate impressive…

Modern processor advancements have introduced security risks, particularly in the form of microarchitectural timing attacks. High-profile attacks such as Meltdown and Spectre have revealed critical flaws, compromising the entire system's…

Zero-shot event extraction (ZSEE) remains a significant challenge for large language models (LLMs) due to the need for complex reasoning and domain-specific understanding. Direct prompting often yields incomplete or structurally invalid…

AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy tool outputs. We address this gap by manually annotating failed agent runs and release a…

Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks. Accountability requires understanding of system limit and condition of erroneous predictions, as…

This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution. Unlike existing methods focused on intra-task learning, ICE…

EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…

LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…

Large language model agents are increasingly expected to perform operational work: calling APIs, manipulating files, assembling workflows, and acting inside enterprise systems. Yet the tool layer on which this execution depends is still…

Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents . In the zero-shot setting, existing methods employ LLMs to generate synthetic data to address…

The opacity of AI models necessitates both validation and evaluation before their integration into services. To investigate these models, explainable AI (XAI) employs methods that elucidate the relationship between input features and output…

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…

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…

Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation,…

The rapid growth in web-based services has significantly increased security risks related to user information, as web-based attacks become increasingly sophisticated and prevalent. Traditional security methods frequently struggle to detect…

Current evaluation frameworks for foundation models rely heavily on static, manually curated benchmarks, limiting their ability to capture the full breadth of model capabilities. This paper introduces Active learning for Capability…

In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX. Existing AutoGPT-style techniques have inherent limitations, such as a heavy reliance on precise descriptions for…