Related papers: Purifying Generative LLMs from Backdoors without P…
Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…
Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…
Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…
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…
The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…
Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…
Backdoor attacks creating 'sleeper agents' in large language models (LLMs) pose significant safety risks. This study employs mechanistic interpretability to explore resulting internal structural differences. Comparing clean Qwen2.5-3B…
Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…
As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full…
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…
Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…
Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior…
Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…
Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks. In Natural Language Processing (NLP), DNNs are often backdoored during the fine-tuning process of a large-scale Pre-trained Language Model (PLM) with poisoned…
Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially verified that LLM is doing substantial harm at all stages,…
In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean…
Vision-Language models like CLIP have been shown to be highly effective at linking visual perception and natural language understanding, enabling sophisticated image-text capabilities, including strong retrieval and zero-shot classification…
Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…
Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard method for reducing costs. In such a situation, the attacker can…
It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…