相关论文: Passive Hack-Back Strategies for Cyber Attribution…

Machine learning algorithms are effective in several applications, but they are not as much successful when applied to intrusion detection in cyber security. Due to the high sensitivity to their training data, cyber detectors based on…

Malicious cyber activity is ubiquitous and its harmful effects have dramatic and often irreversible impacts on society. Given the shortage of cybersecurity professionals, the ever-evolving adversary, the massive amounts of data which could…

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

The impact of frontier AI (i.e., AI agents and foundation models) in cybersecurity is rapidly increasing. In this paper, we comprehensively analyze this trend through multiple aspects: quantitative benchmarks, qualitative literature review,…

Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of infected models will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Currently,…

Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipulation, where heterogeneous signals from multiple sources are often incomplete, ambiguous, or…

Deception technology has proven to be a sound approach against threats to information systems. Aside from well-established honeypots, decoy elements, also known as honeytokens, are an excellent method to address various types of threats.…

In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a carefully planted…

The internet landscape is growing and at the same time becoming more heterogeneous. Services are performed via computers and networks, critical data is stored digitally. This enables freedom for the user, and flexibility for operators. Data…

Adversarial environments require agents to navigate a key strategic trade-off: acquiring information enhances situational awareness, but may simultaneously expose them to threats. To investigate this tension, we formulate a…

This paper studies the vehicle bicycle model under three classes of stealthy cyber-attacks: replay attacks, zero dynamics attacks, and covert attacks. Using a system-theoretic framework, we analyze the feasibility and impact of these…

With the widespread application of artificial intelligence technologies in face recognition and other fields, data privacy security issues have received extensive attention, especially the \textit{right to be forgotten} emphasized by…

Whilst adversarial attack detection has received considerable attention, it remains a fundamentally challenging problem from two perspectives. First, while threat models can be well-defined, attacker strategies may still vary widely within…

Open-weight general-purpose AI (GPAI) models offer significant benefits but also introduce substantial cybersecurity risks, as demonstrated by the offensive capabilities of models like DeepSeek-R1 in evaluations such as MITRE's OCCULT.…

Nowadays, considering the speed of the processes and the amount of data used in cyber defense, it cannot be expected to have an effective defense by using only human power without the help of automation systems. However, for the effective…

The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web…

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

Keyloggers remain a serious threat in modern cybersecurity, silently capturing user keystrokes to steal credentials and sensitive information. Traditional defenses focus mainly on detection and removal, which can halt malicious activity but…

As Critical National Infrastructures are becoming more vulnerable to cyber attacks, their protection becomes a significant issue for any organization as well as a nation. Moreover, the ability to attribute is a vital element of avoiding…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…