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

Intent-based cross-chain bridges have emerged as an alternative to traditional interoperability protocols by allowing off-chain entities (\emph{solvers}) to immediately fulfill users' orders by fronting their own liquidity. While improving…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management. However, the algorithmic backbone of neural networks is brittle to imperceptible…

Adversarial examples pose a security risk as they can alter decisions of a machine learning classifier through slight input perturbations. Certified robustness has been proposed as a mitigation where given an input $\mathbf{x}$, a…

Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address this vulnerability, we propose a certifiably robust malware detection framework based on…

We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we show that it is possible to conceptualize the creation of…

Mutation analysis is one of the most effective, but costly means of assessing the ability of software test suites to prevent bugs. Traditional mutation analysis involves producing and evaluating syntactic variants of the original to check…

Reactive defense mechanisms, such as intrusion detection systems, have made significant efforts to secure a system or network for the last several decades. However, the nature of reactive security mechanisms has limitations because…

In early 2018, Meltdown first showed how to read arbitrary kernel memory from user space by exploiting side-effects from transient instructions. While this attack has been mitigated through stronger isolation boundaries between user and…

This paper considers a constrained discrete-time linear system subject to actuation attacks. The attacks are modelled as false data injections to the system, such that the total input (control input plus injection) satisfies hard input…

Recent continual learning approaches have primarily focused on mitigating catastrophic forgetting. Nevertheless, two critical areas have remained relatively unexplored: 1) evaluating the robustness of proposed methods and 2) ensuring the…

Side-channel attacks have become a severe threat to the confidentiality of computer applications and systems. One popular type of such attacks is the microarchitectural attack, where the adversary exploits the hardware features to break the…

Billions of dollars have been lost due to vulnerabilities in smart contracts. To counteract this, researchers have proposed attack frontrunning protections designed to preempt malicious transactions by inserting "whitehat" transactions…

Recent results suggest that attacks against supervised machine learning systems are quite effective, while defenses are easily bypassed by new attacks. However, the specifications for machine learning systems currently lack precise…

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by…

Model stealing attacks present a dilemma for public machine learning APIs. To protect financial investments, companies may be forced to withhold important information about their models that could facilitate theft, including uncertainty…

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

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…

Malware remains a big threat to cyber security, calling for machine learning based malware detection. While promising, such detectors are known to be vulnerable to evasion attacks. Ensemble learning typically facilitates countermeasures,…

Machine learning is vulnerable to adversarial examples: inputs carefully modified to force misclassification. Designing defenses against such inputs remains largely an open problem. In this work, we revisit defensive distillation---which is…