相关论文: ISACL: Internal State Analyzer for Copyrighted Tra…

Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in…

To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…

Large language models (LLMs) have transformed natural language processing (NLP), enabling applications from content generation to decision support. Retrieval-Augmented Generation (RAG) improves LLMs by incorporating external knowledge but…

Large language models (LLMs) are increasingly used in sensitive domains, where their ability to infer personal data from seemingly benign text introduces emerging privacy risks. While recent LLM-based anonymization methods help mitigate…

Automating hardware (HW) security vulnerability detection and mitigation during the design phase is imperative for two reasons: (i) It must be before chip fabrication, as post-fabrication fixes can be costly or even impractical; (ii) The…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research. While previous research delved into…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…

Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content similar to their training data, posing potential concerns.…

Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently share confidential data or generate policy-violating content. This paper proposes SafeGPT, a…

The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are…

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

With the rapid progress of large language models (LLMs), many downstream NLP tasks can be well solved given appropriate prompts. Though model developers and researchers work hard on dialog safety to avoid generating harmful content from…

The number and dynamic nature of web and mobile applications presents significant challenges for assessing their compliance with data protection laws. In this context, symbolic and statistical Natural Language Processing (NLP) techniques…

Model adaptation is crucial to handle the discrepancy between proxy training data and actual users data received. To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where…

Recent advances in Retrieval-Augmented Generation (RAG) have enabled large language models (LLMs) to ground outputs in clinical evidence. However, connecting LLMs with external databases introduces the risk of contextual leakage: a subtle…

Background: Leaking sensitive information - such as API keys, tokens, and credentials - in source code remains a persistent security threat. Traditional regex and entropy-based tools often generate high false positives due to limited…

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…