Related papers: When Personalization Legitimizes Risks: Uncovering…

Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy.…

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…

Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions in the memory module for demonstrations, introducing new…

Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks, where adversaries inject malicious instructions through query only interactions that corrupt the agents long term memory and influence…

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests.…

The rapid advancement of conversational agents, particularly chatbots powered by Large Language Models (LLMs), poses a significant risk of social engineering (SE) attacks on social media platforms. SE detection in multi-turn, chat-based…

Large language models (LLMs) typically generate identical or similar responses for all users given the same prompt, posing serious safety risks in high-stakes applications where user vulnerabilities differ widely. Existing safety…

Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…

A growing body of research assumes that large language model (LLM) agents can serve as proxies for how people form attitudes toward and behave in response to security and privacy (S&P) threats. If correct, these simulations could offer a…

LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and…

Personalization is one of the next milestones in advancing AI capability and alignment. We introduce PersonaMem-v2, the state-of-the-art dataset for LLM personalization that simulates 1,000 realistic user-chatbot interactions on 300+…

Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this helpfulness introduces new security risks stem less from direct interface abuse than from…

Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM…

For socially sensitive tasks like hate speech detection, the quality of explanations from Large Language Models (LLMs) is crucial for factors like user trust and model alignment. While Persona prompting (PP) is increasingly used as a way to…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or biased memory accumulation can trigger abnormal agent…

Data containing personal information is increasingly used to train, fine-tune, or query Large Language Models (LLMs). Text is typically scrubbed of identifying information prior to use, often with tools such as Microsoft's Presidio or…

Large language models (LLMs) are used to generate content for a wide range of tasks, and are set to reach a growing audience in coming years due to integration in product interfaces like ChatGPT or search engines like Bing. This intensifies…

Current privacy research on large language models (LLMs) primarily focuses on the issue of extracting memorized training data. At the same time, models' inference capabilities have increased drastically. This raises the key question of…

Most traditional AI safety research has approached AI models as machines and centered on algorithm-focused attacks developed by security experts. As large language models (LLMs) become increasingly common and competent, non-expert users can…