Related papers: Rotated Robustness: A Training-Free Defense agains…

Low rank adaptation (LoRA) has emerged as a prominent technique for fine-tuning large language models (LLMs) thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural…

Large Language Models (LLMs) have greatly pushed forward advancements in natural language processing, yet their high memory and computational demands hinder practical deployment. Binarization, as an effective compression technique, can…

Adversarial attacks on Neural Network weights, such as the progressive bit-flip attack (PBFA), can cause a catastrophic degradation in accuracy by flipping a very small number of bits. Furthermore, PBFA can be conducted at run time on the…

Large Language Models (LLMs) pre-trained on internet-scale datasets have shown impressive capabilities in code understanding, synthesis, and general purpose question-and-answering. Key to their performance is the substantial prior knowledge…

Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible to bit-flip faults caused by hardware degradation, cosmic radiation, or deliberate fault-injection attacks such as Rowhammer. These…

Reinforcement Learning (RL), one of the core paradigms in machine learning, learns to make decisions based on real-world experiences. This approach has significantly advanced AI applications across various domains, notably in smart grid…

The safety alignment of Language Models (LMs) is a critical concern, yet their integrity can be challenged by direct parameter manipulation attacks, such as those potentially induced by fault injection. As LMs are increasingly deployed…

Recent advancements in pre-trained large language models (LLMs) have significantly influenced various domains. Adapting these models for specific tasks often involves fine-tuning (FT) with private, domain-specific data. However, privacy…

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Large Language Models (LLMs) have become indispensable in real-world applications. However, their widespread adoption raises significant safety concerns, particularly in responding to socially harmful questions. Despite substantial efforts…

In recent years, large language models (LLMs) have achieved remarkable advances and are increasingly deployed in critical applications across diverse domains. This growing adoption raises urgent concerns about their security and robustness.…

The evolution of wireless communication systems will be fundamentally impacted by an open radio access network (O-RAN), a new concept defining an intelligent architecture with enhanced flexibility, openness, and the ability to slice…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Multi-modal foundation models like OpenFlamingo, LLaVA, and GPT-4 are increasingly used for various real-world tasks. Prior work has shown that these models are highly vulnerable to adversarial attacks on the vision modality. These attacks…

Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces. In this work, we find that the safety alignment of RVLMs…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted significant security vulnerabilities in fine-tuned LLMs. Existing…

Rotations have become essential to state-of-the-art quantization pipelines for large language models (LLMs) by effectively smoothing outliers in weights and activations. However, further optimizing the rotation parameters offers only…

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Continual learning in Large Language Models (LLMs) faces the critical challenge of balancing stability (retaining old knowledge) and plasticity (learning new tasks). While Experience Replay (ER) is a standard countermeasure against…