Related papers: WeSee: Using Malicious #VC Interrupts to Break AMD…
The widespread adoption of outsourced neural network inference presents significant privacy challenges, as sensitive user data is processed on untrusted remote servers. Secure inference offers a privacy-preserving solution, but existing…
The rise of cloud computing has spurred a trend of transferring data storage and computational tasks to the cloud. To protect confidential information such as customer data and business details, it is essential to encrypt this sensitive…
Applications running in Trusted Execution Environments (TEEs) commonly use untrusted external services such as host File System. Adversaries may maliciously alter the normal service behavior to trigger subtle application bugs that would…
The growth of cloud computing has revolutionized data processing and storage capacities to another levels of scalability and flexibility. But in the process, it has created a huge challenge of security, especially in terms of safeguarding…
Stream processing systems are important in modern applications in which data arrive continuously and need to be processed in real time. Because of their resource and scalability requirements, many of these systems run on the cloud, which is…
Securing neural networks (NNs) against model extraction and parameter exfiltration attacks is an important problem primarily because modern NNs take a lot of time and resources to build and train. We observe that there are no…
Large Vision-Language Models (LVLMs), trained on multimodal big datasets, have significantly advanced AI by excelling in vision-language tasks. However, these models remain vulnerable to adversarial attacks, particularly jailbreak attacks,…
The popularity of the Java programming language has led to its wide adoption in cloud computing infrastructures. However, Java applications running in untrusted clouds are vulnerable to various forms of privileged attacks. The emergence of…
We present a new type of attack in which source code is maliciously encoded so that it appears different to a compiler and to the human eye. This attack exploits subtleties in text-encoding standards such as Unicode to produce source code…
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…
In computer vision, the vision transformer (ViT) has increasingly superseded the convolutional neural network (CNN) for improved accuracy and robustness. However, ViT's large model sizes and high sample complexity make it difficult to train…
Perception module of Autonomous vehicles (AVs) are increasingly susceptible to be attacked, which exploit vulnerabilities in neural networks through adversarial inputs, thereby compromising the AI safety. Some researches focus on creating…
On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing (e.g., AnyRes) introduces an inherent algorithmic side-channel.…
Virtual reality (VR), while enhancing user experiences, introduces significant privacy risks. This paper reveals a novel vulnerability in VR systems that allows attackers to capture VR privacy through obstacles utilizing millimeter-wave…
In the modern Systems-on-Chip (SoC), the Advanced eXtensible Interface (AXI) protocol exhibits security vulnerabilities, enabling partial or complete denial-of-service (DoS) through protocol-violation attacks. The recent countermeasures…
Trusted Execution Environments (TEE) are used to safeguard on-device models. However, directly employing TEEs to secure the entire DNN model is challenging due to the limited computational speed. Utilizing GPU can accelerate DNN's…
Since its debut, SGX has been used in many applications, e.g., secure data processing. However, previous systems usually assume a trusted enclave and ignore the security issues caused by an untrusted enclave. For instance, a vulnerable (or…
Non-volatile memories (NVMs) have the potential to reshape next-generation memory systems because of their promising properties of near-zero leakage power consumption, high density and non-volatility. However, NVMs also face critical…
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work…
It is possible to attack a computer remotely through the front panel LEDs. Following on previous results that showed information leakage at optical wavelengths, now it seems practicable to inject information into a system as well. It is…