相关论文: Chasing the Shadows: TTPs in Action to Attribute A…

As the amount of digital devices suspected of containing digital evidence increases, case backlogs for digital investigations are also increasing in many organizations. To ensure timely investigation of requests, this work proposes the use…

Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior…

In recent years, the adoption of cloud services has been expanding at an unprecedented rate. As more and more organizations migrate or deploy their businesses to the cloud, a multitude of related cybersecurity incidents such as data…

The rapid expansion of Internet use has increased system exposure to cyber threats, with advanced persistent threats (APTs) being especially challenging due to their stealth, prolonged duration, and multi-stage attacks targeting high-value…

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Data attribution methods aim to quantify the influence of individual training samples on the prediction of artificial intelligence (AI) models. As training data plays an increasingly crucial role in the modern development of large-scale AI…

We propose ${\tt AdaTS}$, a Thompson sampling algorithm that adapts sequentially to bandit tasks that it interacts with. The key idea in ${\tt AdaTS}$ is to adapt to an unknown task prior distribution by maintaining a distribution over its…

Given the complexity of multi-tenant cloud environments and the growing need for real-time threat mitigation, Security Operations Centers (SOCs) must adopt AI-driven adaptive defense mechanisms to counter Advanced Persistent Threats (APTs).…

The highest level in the Endsley situation awareness model is called projection when the status of elements in the environment in the near future is predicted. In cybersecurity situation awareness, the projection for an Advanced Persistent…

Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…

Model attribution is a critical component of deep neural networks (DNNs) for its interpretability to complex models. Recent studies bring up attention to the security of attribution methods as they are vulnerable to attribution attacks that…

Trajectory prediction systems are critical for autonomous vehicle safety, yet remain vulnerable to adversarial attacks that can cause catastrophic traffic behavior misinterpretations. Existing attack methods require white-box access with…

Source code attribution approaches have achieved remarkable accuracy thanks to the rapid advances in deep learning. However, recent studies shed light on their vulnerability to adversarial attacks. In particular, they can be easily deceived…

Failure attribution, i.e., identifying the responsible agent and decisive step of a failure, is particularly challenging in LLM-based multi-agent systems (MAS) due to their natural-language reasoning, nondeterministic outputs, and intricate…

Activation Patching is a method of directly computing causal attributions of behavior to model components. However, applying it exhaustively requires a sweep with cost scaling linearly in the number of model components, which can be…

MITRE ATT&CK is a cybersecurity knowledge base that organizes threat actor and cyber-attack information into a set of tactics describing the reasons and goals threat actors have for carrying out attacks, with each tactic having a set of…

Current Transferable Adversarial Examples (TAE) are primarily generated by adding Adversarial Noise (AN). Recent studies emphasize the importance of optimizing Data Augmentation (DA) parameters along with AN, which poses a greater threat to…

Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced estimation errors for crowd counting missions. Recent studies…

Advanced persistent threats (APTs) have novel features such as multi-stage penetration, highly-tailored intention, and evasive tactics. APTs defense requires fusing multi-dimensional Cyber threat intelligence data to identify attack…

Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-tuning. We introduce Persona-Conditioned Adversarial Prompting (PCAP), which conditions…