Related papers: Prompt as Triggers for Backdoor Attack: Examining …

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness…

Backdoor attacks pose a significant threat to the integrity of text classification models used in natural language processing. While several dirty-label attacks that achieve high attack success rates (ASR) have been proposed, clean-label…

In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired target label when a predefined trigger is added to test…

Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1) Semantic Consistency, where backdoor prompts tend to…

It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threatening backdoor attack…

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Graph Prompt Learning (GPL) has been introduced as a promising approach that uses prompts to adapt pre-trained GNN models to specific downstream tasks without requiring fine-tuning of the entire model. Despite the advantages of GPL, little…

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…

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Backdoor attacks are a significant threat to the performance and integrity of pre-trained language models. Although such models are routinely fine-tuned for downstream NLP tasks, recent work shows they remain vulnerable to backdoor attacks…

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications. However, studies that explore their vulnerabilities emerging from malicious user…

Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions. The widespread use of LLMs holds significant potential for…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Large language models are increasingly used for vulnerability detection, yet their reliability under different prompt formulations remains uncharacterized. We present PromptAudit, a controlled evaluation framework that isolates prompt…