Related papers: Patronus: Identifying and Mitigating Transferable …

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,…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced by attackers, is becoming increasingly critical for machine learning security and integrity. Fine-tuning based on benign data is a natural…

Federated Learning (FL) enables multiple clients to collaboratively train a shared model without exposing local data. However, backdoor attacks pose a significant threat to FL. These attacks aim to implant a stealthy trigger into the global…

Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable components opens entry points for attackers. Threats have…

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients'…

Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms…

Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increasingly complex and often require high computational resources…

Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor…

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

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…

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks. We present the first backdoor attack framework, BadCSE, for state-of-the-art sentence…

As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model repairing or input robustness, yet these approaches are often…