The paper proposes using Trusted-Execution Environments (TEEs) to create a scalable, privacy-preserving system where authors can submit cryptographic proofs of correct research replication, thereby ad…

The paper investigates how users perceive and utilize security and privacy transparency in consumer-facing generative AI, finding that users rely on proxies like popularity and require actionable, tru…

The paper introduces SymTEE, an LLM-assisted symbolic execution framework that detects missing input validation vulnerabilities in TEE applications without needing complex, real TEE setups.

The paper introduces a new benchmark and decomposition method, Sufficiency-Tightness Decomposition, demonstrating that current coding agents struggle to accurately infer least-privilege authorization,…

The paper introduces a validated, consensus-labeled prompt bank that separates requests for executable malicious code (weapons) from requests for general harmful security knowledge, providing a more g…

The paper investigates how AI coding assistants shift developers' security focus from proactive prevention to reactive review, finding that this structural change is reinforced by current tool interac…

The paper proposes an evidence-driven protocol combining Deterministic Build Systems and Trusted Execution Environments to provide cryptographically verifiable guarantees of software artifact integrit…

This paper proposes an empirical methodology to automate web application trustworthiness assessment by leveraging Large Language Models (LLMs) to verify adherence to secure coding practices, showing t…

The paper tested the hypothesis that wrapping untrusted prompt inputs in mock tool calls would improve LLM robustness, but found that this technique generally fails and can even increase vulnerability…

This survey analyzed 132 web application security tutorials, finding that most lack concrete implementation details and recommending that the presence of runnable code and links to official resources…

The paper introduces TEERepair, a framework that automatically repairs severe security vulnerabilities caused by improper partitioning in Trusted Execution Environments (TEEs) by combining a domain-sp…

Styx is a novel framework that enhances data privacy and security in collaborative data processing, such as joint AI training, by integrating sticky policies with Trusted Execution Environments (TEEs)…

The paper investigates how LLM agents determine the security of their execution environment in a simulated negotiation setting, finding that while they can detect danger, they cannot reliably verify s…

This paper provides a large-scale empirical analysis of indirect prompt injections found in webpages, revealing that prompt-based interference is a widespread, persistent, and growing threat targeting…

The paper introduces ASPI, a benchmark showing that requiring LLM agents to seek clarification significantly amplifies their vulnerability to prompt injection attacks.

The paper introduces the Mitigation-Aware Chain-of-Thought (MA-CoT) framework, which significantly enhances the security reliability of code generated by LLMs across multiple languages and models.

The paper reports on penetration tests conducted on proprietary, large-scale AI agent systems, finding that security vulnerabilities persist despite stricter development standards.

The paper empirically evaluates the security quality of LLM-generated code across various prompting methods, finding that while prompting alters the structure of weaknesses, it is insufficient to reli…

The paper introduces False Security Confidence (FSC), a new metric to measure the inherent prevalence of security vulnerabilities in code generated by LLMs that are otherwise functionally correct, eve…

This paper provides the first comprehensive review of threats and defenses specifically targeting on-device AI inference, revealing a significant imbalance where certain attack types, like adversarial…