Related papers: When One Modality Rules Them All: Backdoor Modalit…
Deep neural networks face persistent challenges in defending against backdoor attacks, leading to an ongoing battle between attacks and defenses. While existing backdoor defense strategies have shown promising performance on reducing attack…
Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial…
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…
As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other. In backdoor…
The success of deep learning has enabled advances in multimodal tasks that require non-trivial fusion of multiple input domains. Although multimodal models have shown potential in many problems, their increased complexity makes them more…
In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…
The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…
Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these…
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…
Autonomous Vehicle decisions rely on multimodal prediction models that account for multiple route options and the inherent uncertainty in human behavior. However, models can suffer from mode collapse, where only the most likely mode is…
Multimodal sentiment analysis (MSA) aims to understand human emotions by integrating information from multiple modalities, such as text, audio, and visual data. However, existing methods often suffer from spurious correlations both within…
Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…
Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…
Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive…
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…
Multi-modal learning has achieved remarkable success by integrating information from various modalities, achieving superior performance in tasks like recognition and retrieval compared to uni-modal approaches. However, real-world scenarios…
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…
Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of…
Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…
Masked diffusion language models (MDLMs) are emerging as a compelling new paradigm for text generation, but their training-time security remains largely unexplored. Existing backdoor attacks on Gaussian diffusion models or autoregressive…