Related papers: BadMerging: Backdoor Attacks Against Model Merging
Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In…
Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this…
Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…
The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats…
Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving software quality, and enhancing operational efficiency. This…
Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…
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…
Deep learning has come a long way and has enjoyed an unprecedented success. Despite high accuracy, however, deep models are brittle and are easily fooled by imperceptible adversarial perturbations. In contrast to common inference-time…
Large-scale deep learning models with a pretraining-finetuning paradigm have led to a surge of numerous task-specific models fine-tuned from a common pre-trained model. Recently, several research efforts have been made on merging these…
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…
Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…
Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented…
Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require access to victim models which may significantly reduce their…
The rapid proliferation of pretrained models and open repositories has made model merging a convenient yet risky practice, allowing free-riders to combine fine-tuned models into a new multi-capability model without authorization. Such…
In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where…
Backdoor attacks are dangerous and difficult to prevent in federated learning (FL), where training data is sourced from untrusted clients over long periods of time. These difficulties arise because: (a) defenders in FL do not have access to…
Evasion attacks are a threat to machine learning models, where adversaries attempt to affect classifiers by injecting malicious samples. An alarming side-effect of evasion attacks is their ability to transfer among different models: this…
The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…
Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream…
Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In…