Related papers: Talk is (Not) Cheap: A Taxonomy and Benchmark Cove…

Large language models (LLMs) have shown promise for automated patching, but their effectiveness depends strongly on how they are integrated into patching systems. While prior work explores prompting strategies and individual agent designs,…

LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime values enter a natural-language prompt, undergo opaque processing inside the LLM, and re-emerge as…

Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function…

Automated building facade inspection is a critical component of urban resilience and smart city maintenance. Traditionally, this field has relied on specialized discriminative models (e.g., YOLO, Mask R-CNN) that excel at pixel-level…

Hyperscale large language model (LLM) inference places extraordinary demands on cloud systems, where even brief failures can translate into significant user and business impact. To better understand and mitigate these risks, we present one…

Repository-level issue resolution benchmarks have become a standard testbed for evaluating LLM-based agents, yet success is still predominantly measured by test pass rates. In practice, however, acceptable patches must also comply with…

Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is…

Large Language Models (LLMs) and Multi-Agent LLMs (MALLMs) introduce non-determinism unlike traditional or machine learning software, requiring new approaches to verifying correctness beyond simple output comparisons or statistical accuracy…

The notion of Attack Surface refers to the critical points on the boundary of a software system which are accessible from outside or contain valuable content for attackers. The ability to identify attack surface components of software…

We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM agent X on the task of Cyber Threat Investigation through security questions derived from investigation graphs. Real-world security analysts must sift through a large number…

Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions,…

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…

Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and…

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…

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their original settings, but their attacks vary substantially in…

Defenses against indirect prompt injection (IPI) in tool-using LLM agents share two structural weaknesses. First, they all attempt to prevent attacks rather than detect the compromises that slip through. Second, they have only been…

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues,…