Related papers: Leaking Secrets through Modern Branch Predictor in…

Side-channel risks of Intel's SGX have recently attracted great attention. Under the spotlight is the newly discovered page-fault attack, in which an OS-level adversary induces page faults to observe the page-level access patterns of a…

Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to…

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill The Beans, a novel application of cache side-channels to…

We present CureSpec, the first model-checking based framework for automatic repair of programs with respect to information leaks in the presence of side-channels and speculative execution. CureSpec is based on formal models of attacker…

There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning…

Quantum circuit cutting enables near-term quantum devices to execute workloads exceeding their qubit capacity by decomposing circuits into independently runnable fragments. While this extends computational reach, it creates a previously…

A recent discovery of a new class of microarchitectural attacks called Spectre picked up the attention of the security community as these attacks can circumvent many traditional mechanisms of defense. One of the attacks---Bounds Check…

The efficacy of address space layout randomization has been formally demonstrated in a shared-memory model by Abadi et al., contingent on specific assumptions about victim programs. However, modern operating systems, implementing layout…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

As the focus on security of Artificial Intelligence (AI) is becoming paramount, research on crafting and inserting optimal adversarial perturbations has become increasingly critical. In the malware domain, this adversarial sample generation…

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…

We present a taxonomy and an algebra for attack patterns on component-based operating systems. In a multilevel security scenario, where isolation of partitions containing data at different security classifications is the primary security…

LFENCE/JMP is an existing software mitigation option for Branch Target Injection (BTI) and similar transient execution attacks stemming from indirect branch predictions, which is commonly used on AMD processors. However, the effectiveness…

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Monumental advancements in artificial intelligence (AI) have lured the interest of doctors, lenders, judges, and other professionals. While these high-stakes decision-makers are optimistic about the technology, those familiar with AI…

The demand for large language model inference is rapidly increasing. Pipeline parallelism offers a cost-effective deployment strategy for distributed inference but suffers from high service latency. While incorporating speculative decoding…

Timing-based side or covert channels in processor caches continue to present a threat to computer systems, and they are the key to many of the recent Spectre and Meltdown attacks. Based on improvements to an existing three-step model for…

Spectre v1 information disclosure attacks, which exploit CPU conditional branch misprediction, remain unsolved in deployed software. Certain Spectre v1 gadgets can be exploited only by out-of-place mistraining, in which the attacker…

Dynamic quantum circuits enable adaptive operations through intermediate measurements and classical feedback. Current transpilation toolchains, such as Qiskit and T$\ket{\text{ket}}$, however, fail to fully exploit branch-specific…

Covert channel networks are a well-known method for circumventing the security measures organizations put in place to protect their networks from adversarial attacks. This paper introduces a novel method based on bit-rate modulation for…