Related papers: Speculative Interference Attacks: Breaking Invisib…
Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…
Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…
Modern prefetchers identify memory access patterns in order to predict future accesses. However, many applications exhibit irregular access patterns that do not manifest spatio-temporal locality in the memory address space. Such…
Since the advent of Spectre attacks, researchers and practitioners have developed a range of hardware and software measures to counter transient execution attacks. A prime example of such mitigation is speculative load hardening in LLVM,…
Computational efficiency has remained a critical consideration in scaling high-capacity language models, with inference latency and resource consumption presenting significant constraints on real-time applications. The study has introduced…
Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure, yet most adversarial attacks change intensities or event counts instead of timing. We study a timing-only adversary that retimes existing spikes…
Contract scheduling is a general technique that allows to design a system with interruptible capabilities, given an algorithm that is not necessarily interruptible. Previous work on this topic has largely assumed that the interruption is a…
Signed social networks are widely used to model the trust relationships among online users in security-sensitive systems such as cryptocurrency trading platforms, where trust prediction plays a critical role. In this paper, we investigate…
Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs). However, this improved accuracy comes at the cost of high…
Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free…
Transient execution side-channel attacks, such as Spectre, have been shown to break almost all isolation primitives. We introduce a new security property we call relaxed microarchitectural isolation (RMI) that allows sensitive programs that…
Task-based programming models have demonstrated their efficiency in the development of scientific applications on modern high-performance platforms. They allow delegation of the management of parallelization to the runtime system (RS),…
We propose a framework for cyber risk assessment and mitigation which models attackers as formal planners and defenders as interdicting such plans. We illustrate the value of plan interdiction problems by first modeling network cyber risk…
This paper considers a method of coding the sensor outputs in order to detect stealthy false data injection attacks. An intelligent attacker can design a sequence of data injection to sensors and actuators that pass the state estimator and…
Availability attacks, which poison the training data with imperceptible perturbations, can make the data \emph{not exploitable} by machine learning algorithms so as to prevent unauthorized use of data. In this work, we investigate why these…
In the inference attacks studied in Quantitative Information Flow (QIF), the adversary typically tries to interfere with the system in the attempt to increase its leakage of secret information. The defender, on the other hand, typically…
Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model's parameters is used during each inference. However, to translate this sparsity into practical performance, an expert caching mechanism…
In neural network (NN) security, safeguarding model integrity and resilience against adversarial attacks has become paramount. This study investigates the application of stochastic computing (SC) as a novel mechanism to fortify NN models.…
Attacks, including the manipulation of sensor readings and the modification of actuator commands, pose a significant challenge to the security and privacy of automated systems. This paper considers discrete event systems that can be modeled…
This paper proposes RCP, a new reversible coherence protocol that ensures invisible speculative load execution (ISLE) with low overhead. RCP can be combined with processor mechanisms that eliminate the effects of speculative instructions on…