相关论文: Hidden Ads: Behavior Triggered Semantic Backdoors …

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the…

Recent advances in Large Visual Language Models (LVLMs) have demonstrated impressive performance across various vision-language tasks by leveraging large-scale image-text pretraining and instruction tuning. However, the security…

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Diffusion models have achieved remarkable progress in both image generation and editing. However, recent studies have revealed their vulnerability to backdoor attacks, in which specific patterns embedded in the input can manipulate the…

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Vision Large Language Models (VLLMs) integrate visual data processing, expanding their real-world applications, but also increasing the risk of generating unsafe responses. In response, leading companies have implemented Multi-Layered…

Sustainable monetization of Large Language Models (LLMs) remains a critical open challenge. Traditional search advertising, which relies on static keywords, fails to capture the fleeting, context-dependent user intents--the specific…

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive…

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box model-level backdoor detection. The visual prompt in VP maps…

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Owing to powerful natural language processing and generative capabilities, large language model (LLM) agents have emerged as a promising solution for enhancing recommendation systems via user simulation. However, in the realm of video…

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…

With the rapid advancement of generative AI, users increasingly rely on image-generation models for image design and creation. To achieve faithful outputs, users typically engage in multi-turn interactions during image refinement: a…

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…