Related papers: One Glitch to Rule Them All: Fault Injection Attac…
Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previously unexamined target. In vLLM's Prefix Caching, these blocks exist as a single physical…
Modern operating systems manage and abstract hardware resources, to ensure efficient execution of user workloads. The operating system must securely interface with often untrusted user code while relying on hardware that is assumed to be…
Adversarial attacks by generating examples which are almost indistinguishable from natural examples, pose a serious threat to learning models. Defending against adversarial attacks is a critical element for a reliable learning system.…
Gradient inversion attacks pose significant privacy threats to distributed training frameworks such as federated learning, enabling malicious parties to reconstruct sensitive local training data from gradient communications between clients…
Multi-process concurrency is effective in improving program efficiency and maximizing CPU utilization. The correct execution of concurrency is ensured by the mutual exclusion and synchronization mechanism (MESM) that manages the shared…
User programs recover from hardware exceptions and respond to signals by executing custom handlers that they register specifically for such events. We present SIGY attack, which abuses this programming model on Intel SGX to break the…
A privacy-preserving Support Vector Machine (SVM) computing scheme is proposed in this paper. Cloud computing has been spreading in many fields. However, the cloud computing has some serious issues for end users, such as unauthorized use…
The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstream variants, enabling transferable attacks across…
Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation. While the vulnerability of CNNs to adversarial attacks is a…
Protecting commodity operating systems and applications against malware and targeted attacks has proven to be difficult. In recent years, virtualization has received attention from security researchers who utilize it to harden existing…
FPGAs are now used in public clouds to accelerate a wide range of applications, including many that operate on sensitive data such as financial and medical records. We present ShEF, a trusted execution environment (TEE) for cloud-based…
Recent years have brought microarchitectural security intothe spotlight, proving that modern CPUs are vulnerable toseveral classes of microarchitectural attacks. These attacksbypass the basic isolation primitives provided by the…
GPU clouds have become a popular computing platform because of the cost of owning and maintaining high-performance computing clusters. Many cloud architectures have also been proposed to ensure a secure execution environment for guest…
Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion.…
Large Language Models (LLMs) like GPT-4, LLaMA, and Qwen have demonstrated remarkable success across a wide range of applications. However, these models remain inherently vulnerable to prompt injection attacks, which can bypass existing…
Side-channel attacks on microprocessors, like the RISC-V, exhibit security vulnerabilities that lead to several design challenges. Hence, it is imperative to study and analyze these security vulnerabilities comprehensively. In this paper,…
We propose SANSCrypt, a novel sequential logic encryption scheme to protect integrated circuits against reverse engineering. Previous sequential encryption methods focus on modifying the circuit state machine such that the correct…
Deep learning (DL) accelerators are increasingly deployed on edge devices to support fast local inferences. However, they suffer from a new security problem, i.e., being vulnerable to physical access based attacks. An adversary can easily…
Multi- and many-core processors are becoming increasingly popular in embedded systems. Many of these processors now feature hardware virtualization capabilities, such as the ARM Cortex A15, and x86 processors with Intel VT-x or AMD-V…
The implementation of cryptographic primitives in integrated circuits (ICs) continues to increase over the years due to the recent advancement of semiconductor manufacturing and reduction of cost per transistors. The hardware implementation…