Related papers: UOR: Universal Backdoor Attacks on Pre-trained Lan…
Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however, are effective only for specific pre-defined downstream…
Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we present AnyDoor, a test-time backdoor attack against multimodal…
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…
Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of…
Visual language model (VLM) is rapidly being integrated into safety-critical systems such as autonomous driving, making it an important attack surface for potential backdoor attacks. Existing backdoor attacks mainly rely on unimodal,…
Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning…
Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…
With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning improves LLMs' performance on downstream tasks, it also introduces new security risks, as…
Developers increasingly construct multimodal large language models (MLLMs) by assembling pretrained components,introducing supply-chain attack surfaces.Existing security research primarily focuses on poisoning backbones such as encoders or…
We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropagating through the…
Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers. However, thus…
Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While it assumes semantic equivalence between the original and compiled graphs, we first…
Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, alongside their impressive capabilities, ethical concerns and…
Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications, e.g., medical question-answering, mathematical sciences, and code generation. However, they also exhibit inherent limitations, such…
Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. However,…
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…
Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…
Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed trigger setting (e.g., unusual words) may be easily detected by…