Related papers: Do Coding Agents Understand Least-Privilege Author…
Controlled sharing is fundamental to distributed systems. We consider a capability-based distributed authorization system where a client receives capabilities (access tokens) from an authorization server to access the resources of resource…
A recent trend in object oriented (OO) programming languages is the use of Access Permissions (APs) as an abstraction for controlling concurrent executions of programs. The use of AP source code annotations defines a protocol specifying how…
A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its…
Despite coding agents' advances in handling increasingly complex tasks, their continued tendency to introduce unintended edits, subtle bugs, and scope drift that slip past code review means developers must still decide how much autonomy to…
As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectively remediate harm when prevention fails. We formalize a solution to this neglected…
Access control policies are used to restrict access to sensitive records for authorized users only. One approach for specifying policies is using role based access control (RBAC) where authorization is given to roles instead of users. Users…
Software vulnerabilities are a challenge in cybersecurity. Manual security patches are often difficult and slow to be deployed, while new vulnerabilities are created. Binary code vulnerability detection is less studied and more complex…
A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…
Application partitioning and code offloading are being researched extensively during the past few years. Several frameworks for code offloading have been proposed. However, fewer works attempted to address issues occurred with its…
AI coding agents operate directly on users' filesystems, where they regularly corrupt data, delete files, and leak secrets. Current approaches force a tradeoff between safety and autonomy: unrestricted access risks harm, while frequent…
Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…
Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based attacks that exploit over-privileged tool use. This paper aims to understand and mitigate…
Recent coding agents can generate complete codebases from simple prompts, yet existing evaluations focus on issue-level bug fixing and lag behind end-to-end development. We introduce ProjDevBench, an end-to-end benchmark that provides…
The promise of least-privilege learning -- to find feature representations that are useful for a learning task but prevent inference of any sensitive information unrelated to this task -- is highly appealing. However, so far this concept…
Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential…
The verification of concurrent programs under weak-memory models is a burgeoning effort, owing to the increasing adoption of weak memory in concurrent software and hardware. Release/Acquire has become the standard model for high-performance…
Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…
When robots share the same workspace with other intelligent agents (e.g., other robots or humans), they must be able to reason about the behaviors of their neighboring agents while accomplishing the designated tasks. In practice,…
While powerful, the inherent non-determinism of large language model (LLM) agents limits their application in structured operational environments where procedural fidelity and predictable execution are strict requirements. This limitation…
Coverage closure is the most time-consuming phase of hardware verification, and recent large language model (LLM)-based coding agents offer a promising approach to automated stimulus generation. However, prior LLM-based flows do not…