Related papers: BitHydra: Towards Bit-flip Inference Cost Attack a…
Generative Artificial Intelligence models, such as Large Language Models (LLMs) and Large Vision Models (VLMs), exhibit state-of-the-art performance but remain vulnerable to hardware-based threats, specifically bit-flip attacks (BFAs).…
The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well studied, Bit-Flip Attacks (BFAs) --…
Large Language Models (LLMs) have revolutionized natural language processing (NLP), excelling in tasks like text generation and summarization. However, their increasing adoption in mission-critical applications raises concerns about…
To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper,…
Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks (BFAs),…
Neural networks have shown remarkable performance in various tasks, yet they remain susceptible to subtle changes in their input or model parameters. One particularly impactful vulnerability arises through the Bit-Flip Attack (BFA), where…
To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper,…
Recently, Bit-Flip Attack (BFA) has garnered widespread attention for its ability to compromise software system integrity remotely through hardware fault injection. With the widespread distillation and deployment of large language models…
We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…
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.…
Model integrity of Large language models (LLMs) has become a pressing security concern with their massive online deployment. Prior Bit-Flip Attacks (BFAs) -- a class of popular AI weight memory fault-injection techniques -- can severely…
Deep neural networks (DNNs) are widely deployed on real-world devices. Concerns regarding their security have gained great attention from researchers. Recently, a new weight modification attack called bit flip attack (BFA) was proposed,…
Several important security issues of Deep Neural Network (DNN) have been raised recently associated with different applications and components. The most widely investigated security concern of DNN is from its malicious input, a.k.a…
Security concerns for large language models (LLMs) have recently escalated, focusing on thwarting jailbreaking attempts in discrete prompts. However, the exploration of jailbreak vulnerabilities arising from continuous embeddings has been…
Determining the optimal data mixture for large language model training remains a challenging problem with an outsized impact on performance. In practice, language model developers continue to rely on heuristic exploration since no…
Bit-flip attacks (BFAs) represent a serious threat to Deep Neural Networks (DNNs), where flipping a small number of bits in the model parameters or binary code can significantly degrade the model accuracy or mislead the model prediction in…
As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…
Large language models (LLMs) have demonstrated remarkable performance across various machine learning tasks. Yet the substantial memory footprint of LLMs significantly hinders their deployment. In this paper, we improve the accessibility of…
The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…
Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency. To mitigate this inefficiency, we present Bi-directional Tuning for lossless…