Related papers: TrajGuard: Streaming Hidden-state Trajectory Detec…

Decentralized Exchanges (DEXs), leveraging blockchain technology and smart contracts, have emerged in decentralized finance. However, the DEX project with multi-contract interaction is accompanied by complex state logic, which makes it…

Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across languages, and rely on limited taxonomies that either fail to…

Wireless networks are vulnerable to jamming attacks due to the shared communication medium, which can severely degrade performance and disrupt services. Despite extensive research, current jamming detection methods often rely on simulated…

Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tune models using supervision derived from the final…

Large Language Diffusion Models (LLDMs) exhibit comparable performance to LLMs while offering distinct advantages in inference speed and mathematical reasoning tasks.The precise and rapid generation capabilities of LLDMs amplify concerns of…

Most commonly used language models (LMs) are instruction-tuned and aligned using a combination of fine-tuning and reinforcement learning, causing them to refuse users requests deemed harmful by the model. However, jailbreak prompts can…

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations, often with…

Modern adversarial campaigns unfold as sequences of behavioural phases - Reconnaissance, Lateral Movement, Intrusion, and Exfiltration - each often indistinguishable from legitimate traffic when viewed in isolation. Existing intrusion…

RL-based controllers achieve strong average-case performance in networking tasks such as congestion control and adaptive bitrate streaming. Yet their performance can degrade severely under network conditions where strong performance is…

Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically behind moderation and safety controls. Despite these controls, preventing prompt-based…

A state-feedback watermarking signal design for the detection of replay attacks in linear systems is proposed. The control input is augmented with a random time-delayed term of the system state estimate, in order to secure the system…

As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informative responses while avoiding the disclosure of harmful or…

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the…

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Jailbreak attacks aim to bypass the LLMs' safeguards. While researchers have proposed different jailbreak attacks in depth, they have done so in isolation -- either with unaligned settings or comparing a limited range of methods. To fill…

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Large Language Models (LLMs) remain vulnerable to jailbreak attacks, which attempt to elicit harmful responses from LLMs. The evolving nature and diversity of these attacks pose many challenges for defense systems, including (1) adaptation…

Predicting future motion is crucial in video understanding and controllable video generation. Dense point trajectories are a compact, expressive motion representation, but modeling their future evolution from observed video remains…