Related papers: Erratum Concerning the Obfuscated Gradients Attack…
Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…
Federated learning---multi-party, distributed learning in a decentralized environment---is vulnerable to model poisoning attacks, even more so than centralized learning approaches. This is because malicious clients can collude and send in…
Software obfuscation plays a crucial role in protecting intellectual property in software from reverse engineering attempts. While some obfuscation techniques originate from the obfuscation-reverse engineering arms race, others stem from…
Stochastic approximation (SA) algorithms have been widely applied in minimization problems when the loss functions and/or the gradient information are only accessible through noisy evaluations. Stochastic gradient (SG) descent---a…
Hardware IP protection has been one of the most critical areas of research in the past years. Recently, attacks on hardware IPs (such as reverse engineering or cloning) have evolved as attackers have developed sophisticated techniques.…
Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…
We consider a class of iterative numerical methods and introduce the notion of semiglobally, practically, strictly pseudogradient (SPSP) search directions. We demonstrate the relevance of the SPSP property in modelling a variety of…
Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box…
Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks, where small perturbations intentionally added to the original inputs can fool the classifier. In this paper, we propose a defense method, Featurized…
Class Activation Mapping (CAM) and its gradient-based variants (e.g., GradCAM) have become standard tools for explaining Convolutional Neural Network (CNN) predictions. However, these approaches typically focus on individual logits, while…
Distributed statistical learning has become a popular technique for large-scale data analysis. Most existing work in this area focuses on dividing the observations, but we propose a new algorithm, DDAC-SpAM, which divides the features under…
Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…
Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses…
Deep neural networks have achieved remarkable success in a wide range of classification tasks. However, they remain highly susceptible to adversarial examples - inputs that are subtly perturbed to induce misclassification while appearing…
Federated Learning (FL) facilitates collaborative model training while preserving data locality; however, the exchange of gradients renders the system vulnerable to Gradient Inversion Attacks (GIAs), allowing adversaries to reconstruct…
Strong physical unclonable function (PUF) is a promising solution for device authentication in resourceconstrained applications but vulnerable to machine learning attacks. In order to resist such attack, many defenses have been proposed in…
Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy…
Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…
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…