相关论文: Forensic Issues and Techniques to Improve Security…

Pushdown systems (PDSs) are a natural model for sequential programs, but they can fail to accurately represent the way an assembly stack actually operates. Indeed, one may want to access the part of the memory that is below the current…

Memory corruption vulnerabilities often enable attackers to take control of a target system by overwriting control-flow relevant data (such as return addresses and function pointers), which are potentially stored in close proximity of…

Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synthesis techniques to steal machine learning models even in…

This paper summarizes our work on experimentally analyzing, exploiting, and addressing vulnerabilities in multi-level cell NAND flash memory programming, which was published in the industrial session of HPCA 2017, and examines the work's…

With the availability of large pre-trained models, a modern workflow for building real-world machine learning solutions is to fine-tune such models on a downstream task with a relatively small domain-specific dataset. In such applications,…

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Deep neural networks can be vulnerable to adversarially crafted examples, presenting significant risks to practical applications. A prevalent approach for adversarial attacks relies on the transferability of adversarial examples, which are…

Bayesian inference in function space has gained attention due to its robustness against overparameterization in neural networks. However, approximating the infinite-dimensional function space introduces several challenges. In this work, we…

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

False Data Injection (FDI) attacks are a common form of Cyber-attack targetting smart grids. Detection of stealthy FDI attacks is impossible by the current bad data detection systems. Machine learning is one of the alternative methods…

Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling OODs as in-distribution (ID). A key underlying problem is…

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Eavesdropping attacks in inference systems aim to learn not the raw data, but the system inferences to predict and manipulate system actions. We argue that conventional information security measures can be ambiguous on the adversary's…

Performance variability management is an active research area in high-performance computing (HPC). We focus on input/output (I/O) variability. To study the performance variability, computer scientists often use grid-based designs (GBDs) to…

Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces. However, model extraction attacks threaten these assets by enabling unauthorized source-domain…

Vision transformers have contributed greatly to advancements in the computer vision domain, demonstrating state-of-the-art performance in diverse tasks (e.g., image classification, object detection). However, their high computational…

Sensor attacks compromise the reliability of cyber-physical systems (CPSs) by altering sensor outputs with the objective of leading the system to unsafe system states. This paper studies a probabilistic intrusion detection framework based…

Assertions are widely used for functional validation as well as coverage analysis for both software and hardware designs. Assertions enable runtime error detection as well as faster localization of errors. While there is a vast literature…

False Base Station (FBS) attack has been a severe security problem for the cellular network since 2G era. During handover, the user equipment (UE) periodically receives state information from surrounding base stations (BSs) and uploads it…

Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highly vulnerable to poisoning-based backdoor attacks operating…