Related papers: AWE: Adaptive Agents for Dynamic Web Penetration T…

Large Language Models (LLMs) demonstrate promising capabilities in solving scientific problems but often suffer from the issue of hallucination. While integrating LLMs with tools can mitigate this issue, models fine-tuned on tool usage…

AI Agents are changing the way work gets done, both in consumer and enterprise domains. However, the design patterns and architectures to build highly capable agents or multi-agent systems are still developing, and the understanding of the…

Static Application Security Testing (SAST) tools are essential for identifying software vulnerabilities, but they often produce a high volume of false positives (FPs), imposing a substantial manual triage burden on developers. Recent…

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We…

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

User-facing applications running in modern datacenters exhibit irregular request patterns and are implemented using a multitude of services with tight latency requirements. These characteristics render ineffective existing energy conserving…

Large Language Models (LLMs) exhibit impressive capabilities, but remain susceptible to a growing spectrum of safety risks, including jailbreaks, toxic content, hallucinations, and bias. Existing defenses often address only a single threat…

Large Language Models (LLMs) have demonstrated effectiveness in code generation tasks. To enable LLMs to address more complex coding challenges, existing research has focused on crafting multi-agent systems with agentic workflows, where…

Network Intrusion Detection Systems (NIDS) face important limitations. Signature-based methods are effective for known attack patterns, but they struggle to detect zero-day attacks and often miss modified variants of previously known…

Advanced Persistent Threats (APTs) are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit…

The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…

Numerous open-source and commercial malware detectors are available. However, their efficacy is threatened by new adversarial attacks, whereby malware attempts to evade detection, e.g., by performing feature-space manipulation. In this…

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

Security teams face a challenge: the volume of newly disclosed Common Vulnerabilities and Exposures (CVEs) far exceeds the capacity to manually develop detection mechanisms. In 2025, the National Vulnerability Database published over 48,000…

Watermarking provides a critical safeguard for large language model (LLM) services by facilitating the detection of LLM-generated text. Correspondingly, stealing watermark algorithms (SWAs) derive watermark information from watermarked…

Prompt engineering is an iterative procedure often requiring extensive manual effort to formulate suitable instructions for effectively directing large language models (LLMs) in specific tasks. Incorporating few-shot examples is a vital and…

Traditional data processing pipelines are typically static and handcrafted for specific tasks, limiting their adaptability to evolving requirements. While general-purpose agents and coding assistants can generate code for well-understood…

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has…