相关论文: REFORGE: Multi-modal Attacks Reveal Vulnerable Con…

Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations,…

Retrieval-Augmented Generation (RAG) is applied to solve hallucination problems and real-time constraints of large language models, but it also induces vulnerabilities against retrieval corruption attacks. Existing research mainly explores…

News image captioning aims to produce journalistically informative descriptions by combining visual content with contextual cues from associated articles. Despite recent advances, existing methods struggle with three key challenges: (1)…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving external data to mitigate hallucinations and outdated knowledge issues. Benefiting from the strong ability in facilitating diverse data sources and…

Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferability on other models…

We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demonstrated to outperform state-of-the-art defenses against…

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Adversarial attacks can deceive neural networks by adding tiny perturbations to their input data. Ensemble defenses, which are trained to minimize attack transferability among sub-models, offer a promising research direction to improve…

Transferable adversarial examples are known to cause threats in practical, black-box attack scenarios. A notable approach to improving transferability is using integrated gradients (IG), originally developed for model interpretability. In…

Recent advances in generative models trained on large-scale datasets have made it possible to synthesize high-quality samples across various domains. Moreover, the emergence of strong inversion networks enables not only a reconstruction of…

Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under…

Rising usage of deep neural networks to perform decision making in critical applications like medical diagnosis and financial analysis have raised concerns regarding their reliability and trustworthiness. As automated systems become more…

Large Multimodal Models (LMMs) are increasingly vulnerable to AI-generated extremist content, including photorealistic images and text, which can be used to bypass safety mechanisms and generate harmful outputs. However, existing datasets…

While Large Vision-Language Models (LVLMs) offer powerful capabilities, they pose privacy risks by unintentionally memorizing sensitive personal information. Current unlearning benchmarks attempt to mitigate this using fictitious identities…

Deep learning techniques have shown promising results in image compression, with competitive bitrate and image reconstruction quality from compressed latent. However, while image compression has progressed towards a higher peak…

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…

Diffusion models (DMs) have recently demonstrated remarkable generation capability. However, their training generally requires huge computational resources and large-scale datasets. To solve these, recent studies empower DMs with the…

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…

How can we effectively unlearn selected concepts from pre-trained generative foundation models without resorting to extensive retraining? This research introduces `continual unlearning', a novel paradigm that enables the targeted removal of…