Related papers: PP3D: An In-Browser Vision-Based Defense Against W…
Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this…
Several autonomy pipelines now have core components that rely on deep learning approaches. While these approaches work well in nominal conditions, they tend to have unexpected and severe failure modes that create concerns when used in…
Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art performance by masking…
Malware is becoming increasingly complex and widespread, making it essential to develop more effective and timely detection methods. Traditional static analysis often fails to defend against modern threats that employ code obfuscation,…
To comply with data protection regulations such as the EU General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA), websites widely deploy cookie consent banners to collect users' privacy preferences. In…
Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE header contents. One barrier to incorporating dynamic analysis features has been the…
Machine learning based phishing website detectors (ML-PWD) are a critical part of today's anti-phishing solutions in operation. Unfortunately, ML-PWD are prone to adversarial evasions, evidenced by both academic studies and analyses of…
Real-world face recognition systems are vulnerable to both physical presentation attacks (PAs) and digital forgery attacks (DFs). We aim to achieve comprehensive protection of biometric data by implementing a unified physical-digital…
Deepfake represents a category of face-swapping attacks that leverage machine learning models such as autoencoders or generative adversarial networks. Although the concept of the face-swapping is not new, its recent technical advances make…
Pseudo-LiDAR-based methods for monocular 3D object detection have received considerable attention in the community due to the performance gains exhibited on the KITTI3D benchmark, in particular on the commonly reported validation split.…
RGB camera-based surveillance systems enable human action recognition for public safety and healthcare, yet raise serious privacy concerns. Existing methods rely on post-capture algorithms, which fail to protect privacy during data…
Pixel-wise regression tasks (e.g., monocular depth estimation (MDE) and optical flow estimation (OFE)) have been widely involved in our daily life in applications like autonomous driving, augmented reality and video composition. Although…
Privacy-enhancing technologies (PETs) represent a critical operational challenge for the online advertising industry, requiring substantial infrastructure investment while promising improved consumer privacy protection. Even when PETs may…
Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications such as robotics and situated conversational agents. When MLLMs reason over…
Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of…
The escalating sophistication of cyber-attacks and the widespread utilization of stealth tactics have led to significant security threats globally. Nevertheless, the existing static detection methods exhibit limited coverage, and…
Though deep neural models adopted to realize the perception of autonomous driving have proven vulnerable to adversarial examples, known attacks often leverage 2D patches and target mostly monocular perception. Therefore, the effectiveness…
As generative models achieve great success, tampering and modifying the sensitive image contents (i.e., human faces, artist signatures, commercial logos, etc.) have induced a significant threat with social impact. The backdoor attack is a…
Dynamic Searchable Symmetric Encryption (DSSE) allows secure searches over a dynamic encrypted database but suffers from inherent information leakage. Existing passive attacks against DSSE rely on persistent leakage monitoring to infer…
Face anti-spoofing algorithms play a pivotal role in the robust deployment of face recognition systems against presentation attacks. Conventionally, full facial images are required by such systems to correctly authenticate individuals, but…