Related papers: Look Twice before You Leap: A Rational Framework f…
The current "notice and consent" paradigm is broken: consent dialogues are often manipulative, and users cannot realistically read or understand every privacy policy. While recent LLM-based tools empower users seeking active control, many…
Large Language Models (LLMs) have showcased remarkable generalizability in language comprehension and hold significant potential to revolutionize human-computer interaction in smart homes. Existing LLM-based smart home assistants typically…
Large Language Models (LLMs) have shown remarkable capabilities in language understanding and generation. Nonetheless, it was also witnessed that LLMs tend to produce inaccurate responses to specific queries. This deficiency can be traced…
The use of Natural Language Processing (NLP) in highstakes AI-based applications has increased significantly in recent years, especially since the emergence of Large Language Models (LLMs). However, despite their strong performance, LLMs…
The prevalence of mobile devices and Location-Based Services (LBS) necessitate the study of Location Privacy-Preserving Mechanisms (LPPM). However, LPPMs reduce the utility of LBS due to the noise they add to users' locations. Here, we…
We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…
The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key challenge is distinguishing therapeutic empathy from maladaptive validation, where supportive…
As large language models (LLMs) become integral to recruitment processes, concerns about AI-induced bias have intensified. This study examines biases in candidate interview reports generated by Claude 3.5 Sonnet, GPT-4o, Gemini 1.5, and…
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News users and Anthropic Interviewer participants at high precision, given pseudonymous online…
Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability. However, when these…
Privacy policies are widely used by digital services and often required for legal purposes. Many machine learning based classifiers have been developed to automate detection of different concepts in a given privacy policy, which can help…
Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety mechanisms. We present RAID (Refusal-Aware and Integrated Decoding), a framework that…
Decentralized AI agent networks, such as Gaia, allows individuals to run customized LLMs on their own computers and then provide services to the public. However, in order to maintain service quality, the network must verify that individual…
We propose an adversarially robust physical layer authentication (AR-PLA) framework tailored for non-stationary multiple-input multiple-output (MIMO) wireless channels. The framework integrates sequential Bayesian decision-making, deep…
The current cybersecurity landscape is increasingly complex, with traditional Static Application Security Testing (SAST) tools struggling to capture complex and emerging vulnerabilities due to their reliance on rule-based matching.…
Language Models (LMs) typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation (LoRA) has gained the most widespread…
The widespread adoption of Large Language Model (LLM) in commercial and research settings has intensified the need for robust intellectual property protection. Backdoor-based LLM fingerprinting has emerged as a promising solution for this…
Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational…
Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. This paper investigates anonymization methods based on representation…
Data sharing between different organizations is an essential process in today's connected world. However, recently there were many concerns about data sharing as sharing sensitive information can jeopardize users' privacy. To preserve the…