相关论文: EIA: Environmental Injection Attack on Generalist …
LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial…
Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely on heuristics and unrealistic assumptions about model access, offering limited ability to…
Membership Inference Attacks (MIAs) pose a critical privacy threat by enabling adversaries to determine whether a specific sample was included in a model's training dataset. Despite extensive research on MIAs, systematic comparisons between…
Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…
As an indispensable personalized service within Location-Based Social Networks (LBSNs), the Point-of-Interest (POI) recommendation aims to assist individuals in discovering attractive and engaging places. However, the accurate…
Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…
Generative Artificial Intelligence (GAI) stands at the forefront of AI innovation, demonstrating rapid advancement and unparalleled proficiency in generating diverse content. Beyond content creation, GAI has significant analytical abilities…
The analysis of the behaviour of individuals and entities (UEBA) is an area of artificial intelligence that detects hostile actions (e.g. attacks, fraud, influence, poisoning) due to the unusual nature of observed events, by affixing to a…
This study explores the application of generative AI (GenAI) within manual exploitation and privilege escalation tasks in Linux-based penetration testing environments, two areas critical to comprehensive cybersecurity assessments. Building…
Privacy issues on social networks have been extensively discussed in recent years. The user identity linkage (UIL) task, aiming at finding corresponding users across different social networks, would be a threat to privacy if unethically…
The pervasive integration of AI has enabled Offensive AI: the exploitation of AI for malicious ends across the cyber-kill chain. A critical manifestation is the user attribute inference attack, where AI infers sensitive Personally…
Privacy Impact Assessments (PIAs) offer a systematic process for assessing the privacy impacts of a project or system. As a privacy engineering strategy, PIAs are heralded as one of the main approaches to privacy by design, supporting the…
This report summarizes all the MIA experiments (Membership Inference Attacks) of the Embedding Attack Project, including threat models, experimental setup, experimental results, findings and discussion. Current results cover the evaluation…
This paper presents a systematic evaluation of the privacy behaviors and attributes of eight recent, popular browser agents. Browser agents are software that automate Web browsing using large language models and ancillary tooling. However,…
The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue goals across almost all tasks that humans can perform. Despite how useful these systems might be,…
Website hacking is a frequent attack type used by malicious actors to obtain confidential information, modify the integrity of web pages or make websites unavailable. The tools used by attackers are becoming more and more automated and…
Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…
The integration of vision-language-action (VLA) models into embodied AI (EAI) robots is rapidly advancing their ability to perform complex, long-horizon tasks in humancentric environments. However, EAI systems introduce critical security…
Our society increasingly benefits from Artificial Intelligence (AI). Unfortunately, more and more evidence shows that AI is also used for offensive purposes. Prior works have revealed various examples of use cases in which the deployment of…
Retrieval-augmented generation (RAG) systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive…