Related papers: Latent Personality Alignment: Improving Harmlessne…

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Modern language models often rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors. However, they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable advancements, LLMs remain susceptible to jailbreak attacks,…

Aligning large language models (LLMs) typically aim to reflect general human values and behaviors, but they often fail to capture the unique characteristics and preferences of individual users. To address this gap, we introduce the concept…

Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is…

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Personalized alignment is essential for enabling large language models (LLMs) to engage effectively in user-centric dialogue. While recent prompt-based and offline optimization methods offer preliminary solutions, they fall short in…

With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively…

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based…

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to change how it…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

In this work, we consider model robustness of deep neural networks against adversarial attacks from a global manifold perspective. Leveraging both the local and global latent information, we propose a novel adversarial training method…

Large Language Model (LLM)-generated data is increasingly used in software analytics, but it is unclear how this data compares to human-written data, particularly when models are exposed to adversarial scenarios. Adversarial attacks can…

Deep learning models can be fooled by small $l_p$-norm adversarial perturbations and natural perturbations in terms of attributes. Although the robustness against each perturbation has been explored, it remains a challenge to address the…

Pretrained language models (PLMs) perform poorly under adversarial attacks. To improve the adversarial robustness, adversarial data augmentation (ADA) has been widely adopted to cover more search space of adversarial attacks by adding…