10 accepted papers
Multimodal large language models (MLLMs) inevitably memorize sensitive cross-modal information during pretraining, making post-deployment unlearning crucial for safety. Existing methods often evaluate unlearning based on output deviations, neglecting generation quality, which can lead to hallucinati…
Person re-identification (ReID) is a fundamental task in many real-world applications such as pedestrian trajectory tracking. However, advanced deep learning-based ReID models are highly susceptible to adversarial attacks, where imperceptible perturbations to pedestrian images can cause entirely inc
The vulnerability of deep neural networks to adversarial examples poses significant challenges to their reliable deployment. Among existing empirical defenses, adversarial training and robust distillation have proven the most effective. In this paper, we identify a property originally associated wit…
Deep Reinforcement Learning agents are in- creasingly used in safety-critical domains but remain vulnerable to stealthy backdoor attacks. Existing outer-loop attacks face a trade-off be- tween perceptual stealth, poisoning efficiency, and value-function consistency, often making the at- tack ineffec…
Graph Retrieval Augmented Generation (GRAG) is a novel paradigm that takes the naive RAG system a step further by integrating graph information, such as knowledge graph (KGs), into large-scale language models (LLMs) to mitigate hallucination. However, existing GRAG still encounter limitations: 1) si…
Adversarial attack on point clouds plays a vital role in evaluating and improving the adversarial robustness of 3D deep learning models. Current attack methods are mainly applied by point perturbation in a non-manifold manner. In this paper, we formulate a novel manifold attack, which deforms the un…
"Filter pruning is one of the most effective methods to compress deep convolutional networks (CNNs). In this paper, as a key component in filter pruning, We first propose a feature discrimination based filter importance criterion, namely Receptive Field Criterion (RFC). It turns the maximum activati…
Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. However, we observe that a too large number of search steps can hurt accuracy. We aim to obtain strong robustness efficiently using fewer step…
"The vulnerability of DNNs severely limits the application of it in the security-sensitive domains. Most of the existing methods improve the robustness of models from weight optimization, such as adversarial training and regularization. However, the architecture is also a key factor to robustness, w…
Overconfident predictions on out-of-distribution (OOD) samples is a thorny issue for deep neural networks. The key to resolve the OOD overconfidence issue inherently is to build a subset of OOD samples and then suppress predictions on them. This paper proposes the Chamfer OOD examples (CODEs), whose…