相关论文: Effective Backdoor Mitigation in Vision-Language M…

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

In recent years, foundation models (FMs) have solidified their role as cornerstone advancements in the deep learning domain. By extracting intricate patterns from vast datasets, these models consistently achieve state-of-the-art results…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Pre-trained large models for multimodal contrastive learning, such as CLIP, have been widely recognized in the industry as highly susceptible to data-poisoned backdoor attacks. This poses significant risks to downstream model training. In…

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…

Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that…

Large Vision-Language Models (LVLMs) have made significant strides in multimodal comprehension, thanks to extensive pre-training and fine-tuning on large-scale visual datasets. However, despite their robust textual safety mechanisms, they…

The Contrastive Language-Image Pretraining (CLIP) model has significantly advanced vision-language modeling by aligning image-text pairs from large-scale web data through self-supervised contrastive learning. Yet, its reliance on uncurated…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifiers. For instance, adversaries could inject malicious…

Transfer learning from pre-trained encoders has become essential in modern machine learning, enabling efficient model adaptation across diverse tasks. However, this combination of pre-training and downstream adaptation creates an expanded…

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…

Machine learning (ML) models trained on data from potentially untrusted sources are vulnerable to poisoning. A small, maliciously crafted subset of the training inputs can cause the model to learn a "backdoor" task (e.g., misclassify inputs…

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…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

Contrastive pretraining of image-text foundation models, such as CLIP, demonstrated excellent zero-shot performance and improved robustness on a wide range of downstream tasks. However, these models utilize large transformer-based encoders…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…