Related papers: Causality Laundering: Denial-Feedback Leakage in T…
LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting,…
The exponential increase in software vulnerabilities has created an urgent need for automatic vulnerability repair (AVR) solutions. Recent research has formulated AVR as a sequence generation problem and has leveraged large language models…
LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only whether harmful actions can be prevented--it is whether those actions…
Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients'…
Advanced persistent threats (APT) are stealthy cyber-attacks that are aimed at stealing valuable information from target organizations and tend to extend in time. Blocking all APTs is impossible, security experts caution, hence the…
Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reason is that responsibility, despite being widely discussed, remains a subjective and…
Data provenance is a valuable tool for detecting and preventing cyber attack, providing insight into the nature of suspicious events. For example, an administrator can use provenance to identify the perpetrator of a data leak, track an…
In an organization specifically as virtual as cloud there is need for access control systems to constrain users direct or backhanded action that could lead to breach of security. In cloud, apart from owner access to confidential data the…
Confidentiality of the data is being endangered as it has been categorized into false categories which might get leaked to an unauthorized party. For this reason, various organizations are mainly implementing data leakage prevention systems…
Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…
Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…
Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…
We study the detection of transient liquidity erosion ("crumbling quotes") in electronic limit order books, where observable quote deterioration may reflect either mechanical liquidity withdrawal or informational repricing. Using the ABIDES…
LLM-based agents have recently attracted significant attention due to their ability to autonomously invoke relevant tools to accomplish complex tasks. However, recent studies have shown that these agents face severe security risks, which…
Undetected anomalies in time series can trigger catastrophic failures in safety-critical systems, such as chemical plant explosions or power grid outages. Although many detection methods have been proposed, their performance remains unclear…
Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…
Security risk analysis typically treats control effectiveness as a static input, yet controls degrade through configuration drift, depend on monitoring systems that may themselves be degraded, and compete for finite remediation budgets. The…
The generalization capabilities of Large Language Models (LLMs) have led to their widespread deployment across various applications. However, this increased adoption has introduced several security threats, notably in the forms of…
Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…
Side-channel attacks exploit unintended information leakage from system behavior and continue to pose serious privacy risks in modern platforms. Despite extensive prior work, side-channel analysis remains largely manual and fragmented,…