Related papers: SEV-Step: A Single-Stepping Framework for AMD-SEV
Intel Software Guard Extensions (SGX) is a promising hardware-based technology for protecting sensitive computations from potentially compromised system software. However, recent research has shown that SGX is vulnerable to branch-shadowing…
Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can…
Deep learning models have shown impressive performance across a spectrum of computer vision applications including medical diagnosis and autonomous driving. One of the major concerns that these models face is their susceptibility to…
We present Virtual Secure Platform (VSP), the first comprehensive platform that implements a multi-opcode general-purpose sequential processor over Fully Homomorphic Encryption (FHE) for Secure Multi-Party Computation (SMPC). VSP protects…
Designing secure architectures for system-on-chip (SoC) platforms is a highly intricate and time-intensive task, often requiring months of development and meticulous verification. Even minor architectural oversights can lead to critical…
Important memory-bound kernels, such as linear algebra, convolutions, and stencils, rely on SIMD instructions as well as optimizations targeting improved vectorized data traversal and data re-use to attain satisfactory performance. On on…
Adversaries with physical access to a target platform can perform cold boot or DMA attacks to extract sensitive data from the RAM. In response, several main-memory encryption schemes have been proposed to prevent such attacks. Also hardware…
Highly privileged software, such as firmware, is an attractive target for attackers. Thus, BIOS vendors use cryptographic signatures to ensure firmware integrity at boot time. Nevertheless, such protection does not prevent an attacker from…
Malware and cheat developers use fileless execution techniques to evade traditional, signature-based security products. These methods include various types of manual mapping, module stomping, and threadless injection which work entirely…
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…
Despite the fact that cyberattacks are constantly growing in complexity, the research community still lacks effective tools to easily monitor and understand them. In particular, there is a need for techniques that are able to not only track…
Ensembles of separate neural networks (NNs) have shown superior accuracy and confidence calibration over single NN across tasks. To improve the hardware efficiency of ensembles of separate NNs, recent methods create ensembles within a…
Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches break under exploration complexity and intent drift. We propose SEMA, a simple yet…
Modern multi-core processors share cache resources for maximum cache utilization and performance gains. However, this leaves the cache vulnerable to side-channel attacks, where timing differences in shared cache behavior are exploited to…
Despite careful safety alignment, current large language models (LLMs) remain vulnerable to various attacks. To further unveil the safety risks of LLMs, we introduce a Safety Concept Activation Vector (SCAV) framework, which effectively…
Forking attacks against TEEs like Intel SGX can be carried out either by rolling back the application to a previous state, or by cloning the application and by partitioning its inputs across the cloned instances. Current solutions to…
Hardware support for trusted execution in modern CPUs enables tenants to shield their data processing workloads in otherwise untrusted cloud environments. Runtime systems for the trusted execution must rely on an interface to the untrusted…
The transient execution attack is a type of attack leveraging the vulnerability of modern CPU optimization technologies. New attacks surface rapidly. The side-channel is a key part of transient execution attacks to leak data. In this work,…
The deep learning revolution has been enabled in large part by GPUs, and more recently accelerators, which make it possible to carry out computationally demanding training and inference in acceptable times. As the size of machine learning…
Embedded devices are increasingly ubiquitous and their importance is hard to overestimate. While they often support safety-critical functions (e.g., in medical devices and sensor-alarm combinations), they are usually implemented under…