Related papers: Silhouette: Efficient Protected Shadow Stacks for …

Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable…

Cache coherence protocols based on self-invalidation and self-downgrade have recently seen increased popularity due to their simplicity, potential performance efficiency, and low energy consumption. However, such protocols result in memory…

On-device machine learning (ML) introduces new security concerns about model privacy. Storing valuable trained ML models on user devices exposes them to potential extraction by adversaries. The current mainstream solution for on-device…

Backdoor attacks embed malicious triggers into training data, enabling attackers to manipulate neural network behavior during inference while maintaining high accuracy on benign inputs. However, existing backdoor attacks face limitations…

Embedded and Internet-of-Things (IoT) devices are ubiquitous today, and the uprising of several botnets based on them (e.g., Mirai, Ripple20) raises issues about the security of such devices. Especially low-power devices often lack support…

Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…

With the improvements of computing technology, more and more applications embed powerful ARM processors into their devices. These systems can be attacked by redirecting the control-flow of a program to bypass critical pieces of code such as…

Sparse inner product (SIP) has the attractive property of overhead being dominated by the intersection of inputs between parties, independent of the actual input size. It has intriguing prospects, especially for boosting machine learning on…

Confidential computing plays an important role in isolating sensitive applications from the vast amount of untrusted code commonly found in the modern cloud. We argue that it can also be leveraged to build safer and more secure…

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…

Secure Multi-Party Computation (MPC) offers a practical foundation for privacy-preserving machine learning at the edge, with MPC commonly employed to support nonlinear operations. These MPC protocols fundamentally rely on Oblivious Transfer…

Object detection and tracking are challenging tasks for resource-constrained embedded systems. While these tasks are among the most compute-intensive tasks from the artificial intelligence domain, they are only allowed to use limited…

Cryptographic algorithm implementations are vulnerable to Cold Boot attacks, which consist in exploiting the persistence of RAM cells across reboots or power down cycles to read the memory contents and recover precious sensitive data. The…

Stack canaries and shadow stacks are widely deployed mitigations to memory-safety vulnerabilities. While stack canaries are introduced by the compiler and rely on sentry values placed between variables and control data, shadow stack…

Layout camouflaging (LC) is a promising technique to protect chip design intellectual property (IP) from reverse engineers. Most prior art, however, cannot leverage the full potential of LC due to excessive overheads and/or their limited…

Modern computer processors use microarchitectural optimization mechanisms to improve performance. As a downside, such optimizations are prone to introducing side-channel vulnerabilities. Speculative loading of memory, called prefetching, is…

The paper proposes in-memory computing (IMC) solution for the design and implementation of the Advanced Encryption Standard (AES) based cryptographic algorithm. This research aims at increasing the cyber security of autonomous driverless…

Microarchitectural attacks are a significant concern, leading to many hardware-based defense proposals. However, different defenses target different classes of attacks, and their impact on each other has not been fully considered. To raise…

Deploying machine learning (ML) models on user devices can improve privacy (by keeping data local) and reduce inference latency. Trusted Execution Environments (TEEs) are a practical solution for protecting proprietary models, yet existing…

Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train or infer with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud.…