Related papers: This is How You Lose the Transient Execution War

Modern microprocessors depend on speculative execution, creating vulnerabilities that enable transient execution attacks. Prior defenses target speculative data leakage but overlook false dependencies from partial address aliasing, where…

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Modern computer processors use microarchitectural optimization mechanisms to improve performance. As a downside, such optimizations are prone to introducing side-channel vulnerabilities. Speculative loading of memory, called prefetching, is…

Moving Target Defense (MTD) has emerged as a key technique in various security applications as it takes away the attacker's ability to perform reconnaissance for exploiting a system's vulnerabilities. However, most of the existing research…

The Spectre and Meltdown flaws in modern microprocessors represent a new class of attacks that have been difficult to mitigate. The mitigations that have been proposed have known performance impacts. The reported magnitude of these impacts…

Class-incremental continual learning addresses catastrophic forgetting by enabling classification models to preserve knowledge of previously learned classes while acquiring new ones. However, the vulnerability of the models against…

In this paper, we consider the problem of attack-resilient state estimation, that is to reliably estimate the true system states despite two classes of attacks: (i) attacks on the switching mechanisms and (ii) false data injection attacks…

Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn Injection(TTI), a new multi-turn attack technique that…

In any tactical scenario, the successful quantification and triangulation of potential hostile elements is instrumental to minimize any casualties which might be incurred. The most commonly deployed infrastructures to cater to this have…

Transferable adversarial images raise critical security concerns for computer vision systems in real-world, black-box attack scenarios. Although many transfer attacks have been proposed, existing research lacks a systematic and…

Fault-tolerance is critically important in highly-distributed modern cloud applications. Solutions such as Temporal, Azure Durable Functions, and Beldi hide fault-tolerance complexity from developers by persisting execution state and…

The recent Spectre attacks have demonstrated that modern microarchitectural optimizations can make software insecure. These attacks use features like pipelining, out-of-order and speculation to extract information about the memory contents…

Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…

Exploitation techniques targeting intermediate (transit) network nodes in public and private networks have been theoretically known and empirically proven to work for quite some time. However, very little effort has been made to look into…

The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or…

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Despite the deployment of preventive security mechanisms to protect the assets and computing platforms of users, intrusions eventually occur. We propose a novel intrusion survivability approach to withstand ongoing intrusions. Our approach…

Adversarial training is arguably the most popular way to provide empirical robustness against specific adversarial examples. While variants based on multi-step attacks incur significant computational overhead, single-step variants are…

An emerging supply-chain attack due to a backdoor in XZ Utils has been identified. The backdoor allows an attacker to run commands remotely on vulnerable servers utilizing SSH without prior authentication. We have started to collect…

As the complexities of Dynamic Data Driven Applications Systems increase, preserving their resilience becomes more challenging. For instance, maintaining power grid resilience is becoming increasingly complicated due to the growing number…