Related papers: CacheTrap: Unveiling a Stealthier Gray-Box Trojan …
Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as…
Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates…
The Key Value(KV) cache is an important component for efficient inference in autoregressive Large Language Models (LLMs), but its role as a representation of the model's internal state makes it a potential target for integrity attacks. This…
Recent years have witnessed the emergence of a new paradigm of building natural language processing (NLP) systems: general-purpose, pre-trained language models (LMs) are composed with simple downstream models and fine-tuned for a variety of…
Robotic manipulation policies are increasingly empowered by \textit{large language models} (LLMs) and \textit{vision-language models} (VLMs), leveraging their understanding and perception capabilities. Recently, inference-time attacks…
Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly…
Efficient key-value (KV) cache compression is critical for scaling transformer-based Large Language Models (LLMs) in long sequences and resource-limited settings. Existing methods evict tokens based on their positions or importance scores,…
Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often…
Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…
Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…
Large Language Models (LLMs) such as GPT and Llama2 are increasingly adopted in many safety-critical applications. Their security is thus essential. Even with considerable efforts spent on reinforcement learning from human feedback (RLHF),…
Large language models (LLMs) are widely deployed across various applications, often with safeguards to prevent the generation of harmful or restricted content. However, these safeguards can be covertly bypassed through adversarial…
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),…
Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced…
Large language models (LLMs) are becoming an integrated part of software development. These models are trained on large datasets for code, where it is hard to verify each data point. Therefore, a potential attack surface can be to inject…
Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…
Large language models (LLMs) have demonstrated exceptional capabilities in generating text, images, and video content. However, as context length grows, the computational cost of attention increases quadratically with the number of tokens,…
Even when prompts and parameters are secured, transformer language models remain vulnerable because their key-value (KV) cache during inference constitutes an overlooked attack surface. This paper introduces Malicious Token Injection (MTI),…
Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns about security vulnerabilities. Existing backdoor attacks against VLMs primarily rely on…
Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previously unexamined target. In vLLM's Prefix Caching, these blocks exist as a single physical…