Related papers: MANATEE: Inference-Time Lightweight Diffusion Base…

Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is…

In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their…

Large language models excel at performing inference over text to extract information, summarize information, or generate additional text. These inference capabilities are implicated in a variety of ethical harms spanning surveillance, labor…

As Large Language Models (LLMs) become ubiquitous, the challenge of securing them against adversarial "jailbreaking" attacks has intensified. Current defense strategies often rely on computationally expensive external classifiers or brittle…

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional conditioning. However, the safety risks posed by jailbreak attacks that exploit this inference…

Safety, security, and compliance are essential requirements when aligning large language models (LLMs). However, many seemingly aligned LLMs are soon shown to be susceptible to jailbreak attacks. These attacks aim to circumvent the models'…

Recently, large language models (LLMs) have been gaining a lot of interest due to their adaptability and extensibility in emerging applications, including communication networks. It is anticipated that ZSM networks will be able to support…

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can…

This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks. Typical DNN classifiers encode the input image into a compressed latent representation more…

Deep convolutional neural networks are susceptible to adversarial attacks. They can be easily deceived to give an incorrect output by adding a tiny perturbation to the input. This presents a great challenge in making CNNs robust against…

Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise and rapid generation capabilities of LLDMs amplify concerns of…

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF). In…

As large language models (LLMs) grow more powerful, ensuring their safety against misuse becomes crucial. While researchers have focused on developing robust defenses, no method has yet achieved complete invulnerability to attacks. We…

A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…

Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset. Existing attack methods have commonly…

Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation efficiency. Beyond the utility benefits, we argue that D-LLMs exhibit a previously underexplored…

Data lakes enable the training of powerful machine learning models on sensitive, high-value medical datasets, but also introduce serious privacy risks due to potential leakage of protected health information. Recent studies show adversaries…