相关论文: Valkyrie: A Response Framework to Augment Runtime …

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

In this paper, we introduce new learning algorithms for reducing false positives in intrusion detection. It is based on decision tree-based attribute weighting with adaptive na\"ive Bayesian tree, which not only reduce the false positives…

Ransomware has been an ongoing issue since the early 1990s. In recent times ransomware has spread from traditional computational resources to cyber-physical systems and industrial controls. We devised a series of experiments in which…

We demonstrate a practical countermeasure against a well-known class of attacks on quantum key distribution (QKD) systems that exploit detection efficiency mismatch, where the receiver's detectors do not exhibit identical responses to…

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

Phishing attacks pose a significant threat to Internet users, with cybercriminals elaborately replicating the visual appearance of legitimate websites to deceive victims. Visual similarity-based detection systems have emerged as an…

In the very last years, cybersecurity attacks have increased at an unprecedented pace, becoming ever more sophisticated and costly. Their impact has involved both private/public companies and critical infrastructures. At the same time, due…

Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attacks possible. We demonstrate that existing observation-space…

Modern software supply chains face an increasing threat from malicious code hidden in trusted components such as browser extensions, IDE extensions, and open-source packages. This paper introduces JavaSith, a novel client-side framework for…

Cybercrimes are on the rise, in part due to technological advancements, as well as increased avenues of exploitation. Sophisticated threat actors are leveraging on such advancements to execute their malicious intentions. The increase in…

This paper presents a novel data-driven framework to aid in system state estimation when the power system is under unobservable false data injection attacks. The proposed framework dynamically detects and classifies false data injection…

Eliminating vulnerabilities from low-level code is vital for securing software. Static analysis is a promising approach for discovering vulnerabilities since it can provide developers early feedback on the code they write. But, it presents…

Sophisticated phishing attacks have emerged as a major cybersecurity threat, becoming more common and difficult to prevent. Though machine learning techniques have shown promise in detecting phishing attacks, they function mainly as "black…

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

Rapid adoption of AI technologies raises several major security concerns, including the risks of adversarial perturbations, which threaten the confidentiality and integrity of AI applications. Protecting AI hardware from misuse and diverse…

In cyber-physical systems, malicious and resourceful attackers could penetrate the system through cyber means and cause significant physical damage. Consequently, detection of such attacks becomes integral towards making these systems…

Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, however, suffer from various kinds of threats, such as…

In order to ensure the quality of software and prevent attacks from hackers on critical systems, static analysis tools are frequently utilized to detect vulnerabilities in the early development phase. However, these tools often report a…

Preventing data exfiltration from computer systems typically depends on perimeter defences, but these are becoming increasingly fragile. Instead we suggest an approach in which each at-risk document is supplemented by many fake versions of…

Artificial intelligence (AI) is increasingly being used to augment and automate cyber operations, altering the scale, speed, and accessibility of malicious activity. These shifts raise urgent questions about when AI systems introduce…