Related papers: GATEBLEED: Exploiting On-Core Accelerator Power Ga…
The rise of Generative AI (GenAI) has reshaped the cybersecurity landscape by enabling new attack vectors and lowering the barrier for executing advanced social engineering campaigns. This study conducts an empirical analysis of…
Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine current business models where a model owner sells model access, e.g., via MLaaS APIs.…
Intel software guard extensions (SGX) aims to provide an isolated execution environment, known as an enclave, for a user-level process to maximize its confidentiality and integrity. In this paper, we study how uninitialized data inside a…
6G -- sixth generation -- is the latest cellular technology currently under development for wireless communication systems. In recent years, machine learning algorithms have been applied widely in various fields, such as healthcare,…
Deploying deep neural networks (DNNs) on edge devices exposes valuable intellectual property to model-stealing attacks. While TEE-shielded DNN partitioning (TSDP) mitigates this by isolating sensitive computations, existing paradigms fail…
In this paper we show how attackers can covertly leak data (e.g., encryption keys, passwords and files) from highly secure or air-gapped networks via the row of status LEDs that exists in networking equipment such as LAN switches and…
Federated learning enables multiple clients to collaboratively contribute to the learning of a global model orchestrated by a central server. This learning scheme promotes clients' data privacy and requires reduced communication overheads.…
An attack on deep learning systems where intelligent machines collaborate to solve problems could cause a node in the network to make a mistake on a critical judgment. At the same time, the security and privacy concerns of AI have…
Shared cache resources in multi-core processors are vulnerable to cache side-channel attacks. Recently proposed defenses have their own caveats: Randomization-based defenses are vulnerable to the evolving attack algorithms besides relying…
The adoption of machine learning solutions is rapidly increasing across all parts of society. As the models grow larger, both training and inference of machine learning models is increasingly outsourced, e.g. to cloud service providers.…
The last level cache is vulnerable to timing based side channel attacks because it is shared by the attacker and the victim processes even if they are located on different cores. These timing attacks evict the victim cache lines using small…
Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications, where privacy is paramount. This paper introduces Whisper Leak, a side-channel attack that…
Recent transient-execution attacks, such as RIDL, Fallout, and ZombieLoad, demonstrated that attackers can leak information while it transits through microarchitectural buffers. Named Microarchitectural Data Sampling (MDS) by Intel, these…
Graphics Processing Units (GPUs) are a ubiquitous component across the range of today's computing platforms, from phones and tablets, through personal computers, to high-end server class platforms. With the increasing importance of graphics…
Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…
Privacy and security have rapidly emerged as priorities in system design. One powerful solution for providing both is privacy-preserving computation, where functions are computed directly on encrypted data and control can be provided over…
Diffusion models (DMs) have emerged as powerful tools for high-quality content generation, yet their intensive computational requirements for inference pose challenges for resource-constrained edge devices. Cloud-based solutions aid in…
Recent research has demonstrated that Intel's SGX is vulnerable to software-based side-channel attacks. In a common attack, the adversary monitors CPU caches to infer secret-dependent data accesses patterns. Known defenses have major…
AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…
Differentially private SGD (DPSGD) has recently shown promise in deep learning. However, compared to non-private SGD, the DPSGD algorithm places computational overheads that can undo the benefit of batching in GPUs. Micro-batching is a…