Related papers: Dynamic Attention Analysis for Backdoor Detection …

Text-to-image diffusion models rely on text embeddings from a pre-trained text encoder, but these embeddings remain fixed across all diffusion timesteps, limiting their adaptability to the generative process. We propose Diffusion Adaptive…

Recently, detecting AI-generated images produced by diffusion-based models has attracted increasing attention due to their potential threat to safety. Among existing approaches, reconstruction-based methods have emerged as a prominent…

Text-to-image (T2I) diffusion models (DMs) have shown promise in generating high-quality images from textual descriptions. The real-world applications of these models require particular attention to their safety and fidelity, but this has…

Deepfakes have emerged as a significant threat to digital media authenticity, increasing the need for advanced detection techniques that can identify subtle and time-dependent manipulations. CNNs are effective at capturing spatial artifacts…

Black-box adversarial attacks remain challenging due to limited access to model internals. Existing methods often depend on specific network architectures or require numerous queries, resulting in limited cross-architecture transferability…

With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious threat: an adversary who poisons a small fraction of training data can implant a hidden…

Recently, 3D backdoor attacks have posed a substantial threat to 3D Deep Neural Networks (3D DNNs) designed for 3D point clouds, which are extensively deployed in various security-critical applications. Although the existing 3D backdoor…

Backdoors can be injected into NLP models to induce misbehavior when the input text contains a specific feature, known as a trigger, which the attacker secretly selects. Unlike fixed words, phrases, or sentences used in the static text…

Contrastive Analysis (CA) detects anomalies by contrasting patterns unique to a target group (e.g., unhealthy subjects) from those in a background group (e.g., healthy subjects). In the context of brain MRIs, existing CA approaches rely on…

Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…

Deep neural networks are known to be vulnerable to unseen data: they may wrongly assign high confidence stcores to out-distribuion samples. Recent works try to solve the problem using representation learning methods and specific metrics. In…

Diffusion models (DMs) have revolutionized data generation, particularly in text-to-image (T2I) synthesis. However, the widespread use of personalized generative models raises significant concerns regarding privacy violations and copyright…

Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, but their role in diffusion transformers remains unclear. We present a causal analysis in…

Because of the threat of advanced multi-step attacks, it is often difficult for security operators to completely cover all vulnerabilities when deploying remediations. Deploying sensors to monitor attacks exploiting residual vulnerabilities…

Deep learning-based lane detection (LD) plays a critical role in autonomous driving systems, such as adaptive cruise control. However, it is vulnerable to backdoor attacks. Existing backdoor attack methods on LD exhibit limited…

We introduce Diffusion Augmented Agents (DAAG), a novel framework that leverages large language models, vision language models, and diffusion models to improve sample efficiency and transfer learning in reinforcement learning for embodied…

Diffusion models have found valuable applications in anomaly detection by capturing the nominal data distribution and identifying anomalies via reconstruction. Despite their merits, they struggle to localize anomalies of varying scales,…

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper,…

Object detection models deployed in real-world applications such as autonomous driving face serious threats from backdoor attacks. Despite their practical effectiveness,existing methods are inherently limited in both capability and…

Deep learning is widely applied in computer-aided pathological diagnosis, which alleviates the pathologist workload and provide timely clinical analysis. However, most models generally require large-scale annotated data for training, which…