Related papers: Towards Provable (In)Secure Model Weight Release S…

Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source codes, model…

Large Language Models (LLMs) have gained significant popularity recently. LLMs are susceptible to various attacks but can also improve the security of diverse systems. However, besides enabling more secure systems, how well do open source…

In modern cryptography, the secret sharing scheme is an important cryptographic primitive and it is used in various situations. In this paper, a timed-release secret sharing scheme (TR-SS) with information-theoretic security is first…

In recent years, Large Language Models (LLMs) have garnered considerable attention for their remarkable abilities in natural language processing tasks. However, their widespread adoption has raised concerns pertaining to trust and safety.…

A key concern for AI safety remains understudied in the machine learning (ML) literature: how can we ensure users of ML models do not leverage predictions on incorrect personal data to harm others? This is particularly pertinent given the…

We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably…

As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful outputs, present significant risks, with existing studies…

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Safe RL, where an agent…

Distributed machine learning has been widely used in recent years to tackle the large and complex dataset problem. Therewith, the security of distributed learning has also drawn increasing attentions from both academia and industry. In this…

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…

We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contained in that data via the model. The standard method for…

Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query…

Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be deemed harmful.Efforts to mitigate this risk include…

System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications. These instructions may contain sensitive…

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

As Large Language Models (LLMs) become integral to scientific workflows, concerns over the confidentiality and ethical handling of confidential data have emerged. This paper explores data exposure risks through LLM-powered scientific tools,…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

With the ever-growing data and the need for developing powerful machine learning models, data owners increasingly depend on various untrusted platforms (e.g., public clouds, edges, and machine learning service providers) for scalable…

Spurred by the recent rapid increase in the development and distribution of large language models (LLMs) across industry and academia, much recent work has drawn attention to safety- and security-related threats and vulnerabilities of LLMs,…