相关论文: Attacking Delay-based PUFs with Minimal Adversary …

Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…

Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial…

In this work, we examine the potential of Physical Unclonable Functions (PUFs) that have been implemented on NAND Flash memories using programming disturbances to act as sustainable primitives for the purposes of lightweight cryptography.…

State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time…

Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large. To address these challenges, machine learning-based classifiers are commonly employed to detect…

Facial recognition systems are susceptible to both physical and digital attacks, posing significant security risks. Traditional approaches often treat these two attack types separately due to their distinct characteristics. Thus, when being…

Hacking password databases is one of the most frequently reported cyber-attacks. Current password management systems are based on known and public algorithms. Also, many studies have shown that users select weak passwords. Thus, with the…

We introduce Universal and Transferable Adversarial Perturbations (UTAP) for pathology foundation models that reveal critical vulnerabilities in their capabilities. Optimized using deep learning, UTAP comprises a fixed and weak noise…

Hardware-based security primitives have become critical to enhancing information security in the Internet of Things (IoT) era. Physical unclonable functions (PUFs) utilize the inherent variations in the manufacturing process to generate…

The lack of stability is one of the major limitations that constrains PUF from being put in widespread practical use. In this paper, we propose a weak PUF and a strong PUF that are both completely stable with 0% intra-distance. These PUFs…

Most machine learning applications rely on centralized learning processes, opening up the risk of exposure of their training datasets. While federated learning (FL) mitigates to some extent these privacy risks, it relies on a trusted…

The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE…

Website fingerprinting (WF) attacks, usually conducted with the help of a machine learning-based classifier, enable a network eavesdropper to pinpoint which web page a user is accessing through the inspection of traffic patterns. These…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. (2023) marks the…

Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…

Physical unclonable functions (PUFs) are widely considered in secret key generation for resource constrained devices. However, PUFs require additional hardware overhead. In this paper, we focus on developing a PUF-efficient, robust, and…

The delay-based fingerprint embedding was recently proposed to support more users in secure media distribution scenario. In this embedding scheme, some users are assigned the same fingerprint code with only different embedding delay. The…

Face recognition technology has dramatically transformed the landscape of security, surveillance, and authentication systems, offering a user-friendly and non-invasive biometric solution. However, despite its significant advantages, face…

Recently, major progress has been made towards the realisation of quantum internet to enable a broad range of classically intractable applications. These applications such as delegated quantum computation require running a secure…