Related papers: Securing AI Agents with Information-Flow Control
Leading AI developers and startups are increasingly deploying agentic AI systems that can plan and execute complex tasks with limited human involvement. However, there is currently no structured framework for documenting the technical…
In security-critical software applications, confidential information must be prevented from leaking to unauthorized sinks. Static analysis techniques are widespread to enforce a secure information flow by checking a program after…
The cloud model's dependence on massive parallelism and resource sharing exacerbates the security challenge of timing side-channels. Timing Information Flow Control (TIFC) is a novel adaptation of IFC techniques that may offer a way to…
Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities. By interacting with external environments through predefined tools, these agents can carry out complex user…
Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is…
Mobile and IoT applications have greatly enriched our daily life by providing convenient and intelligent services. However, these smart applications have been a prime target of adversaries for stealing sensitive data. It poses a crucial…
As artificial intelligence (AI) becomes deeply embedded in critical services and everyday products, it is increasingly exposed to security threats which traditional cyber defenses were not designed to handle. In this paper, we investigate…
AI agents are increasingly deployed to automate complex enterprise workflows, yet evidence of their effectiveness in identity governance is limited. We report results from the first randomized controlled trial (RCT) evaluating an AI agent…
As generative AI (GenAI) agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act,…
Many important security problems in JavaScript, such as browser extension security, untrusted JavaScript libraries and safe integration of mutually distrustful websites (mash-ups), may be effectively addressed using an efficient…
This study introduces an innovative approach to automating Cyber Threat Intelligence (CTI) processes in industrial environments by leveraging Microsoft's AI-powered security technologies. Historically, CTI has heavily relied on manual…
As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges.…
Building and deploying machine learning solutions in healthcare remains expensive and labor-intensive due to fragmented preprocessing workflows, model compatibility issues, and stringent data privacy constraints. In this work, we introduce…
This paper presents a conceptual and operational framework for developing and operating safe and trustworthy AI agents based on a Three-Pillar Model grounded in transparency, accountability, and trustworthiness. Building on prior work in…
A security policy specifies a security property as the maximal information flow. A distributed system composed of interacting processes implicitly defines an intransitive security policy by repudiating direct information flow between…
Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…
Recent Pwn2Own competitions have demonstrated the continued effectiveness of control hijacking attacks despite deployed countermeasures including stack canaries and ASLR. A powerful defense called Control flow Integrity (CFI) offers a…
The growing system complexity from microservice architectures and the bilateral enhancement of artificial intelligence (AI) for both attackers and defenders presents increasing security challenges for cloud-native operations. In particular,…