Related papers: Surviving the Unseen: Predictive Defense for Novel…

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects by establishing feature mapping between textual prompts and inspection images, demonstrating excellent research value in flexible industrial…

Multivariate time series anomalies often manifest as shifts in cross-channel dependencies rather than simple amplitude excursions. In autonomous driving, for instance, a steering command might be internally consistent but decouple from the…

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…

Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…

Network defenses based on traditional tools, techniques, and procedures fail to account for the attacker's inherent advantage present due to the static nature of network services and configurations. To take away this asymmetric advantage,…

Accurate and robust trajectory prediction is essential for safe and efficient autonomous driving, yet recent work has shown that even state-of-the-art prediction models are highly vulnerable to inputs being mildly perturbed by adversarial…

As Vision-Language Models (VLMs) move into interactive, multi-turn use, safety concerns intensify for multimodal multi-turn dialogue, which is characterized by concealment of malicious intent, contextual risk accumulation, and cross-modal…

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single…

The proliferation of UAVs has enabled a wide range of mission-critical applications and is becoming a cornerstone of low-altitude networks, supporting smart cities, emergency response, and more. However, the open wireless environment,…

The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks could compromise model performance and system security in…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial…

This paper introduces the Adaptive Defense Agent (ADA), an innovative Automated Moving Target Defense (AMTD) system designed to fundamentally enhance the security posture of AI workloads. ADA operates by continuously and automatically…

Multimodal large language models (MLLMs) have revolutionized vision-language understanding but remain vulnerable to multimodal jailbreak attacks, where adversarial inputs are meticulously crafted to elicit harmful or inappropriate…

With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC (Security Operation Centers) analysts are often…

Moving Target Defense (MTD) has emerged as a proactive and dynamic framework to counteract evolving cyber threats. Traditional MTD approaches often rely on assumptions about the attackers knowledge and behavior. However, real-world…