Related papers: CAPTURE: Context-Aware Prompt Injection Testing an…

Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prompt can cause significant discrepancies in model performance.…

The use of unvetted third-party and internet data renders pre-trained models susceptible to backdoor attacks. Detecting backdoor samples is critical to prevent backdoor activation during inference or injection during training. However,…

The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimodal agents, recent advancements in reasoning-heavy models,…

Gaze estimation models are widely used in applications such as driver attention monitoring and human-computer interaction. While many methods for gaze estimation exist, they rely heavily on data-hungry deep learning to achieve high…

Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specified task rather than…

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection…

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing attack methods typically focus on text-image interplay, treating the visual modality as a…

Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general prompt injection attacks, but none have been systematically evaluated for web agents. In this…

The widespread use of Large Language Models (LLMs) in many applications marks a significant advance in research and practice. However, their complexity and hard-to-understand nature make them vulnerable to attacks, especially jailbreaks…

Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity due to its capacity to reduce computational demands through…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

Large language models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information in long context scenarios. To address these…

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities,…

The widespread deployment of text-to-image diffusion models is significantly challenged by the generation of visually harmful content, such as sexually explicit content, violence, and horror imagery. Common safety interventions, ranging…

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

Large language models (LLMs) remain acutely vulnerable to prompt injection and related jailbreak attacks; heuristic guardrails (rules, filters, LLM judges) are routinely bypassed. We present Contextual Integrity Verification (CIV), an…

Recent progress in ML and LLMs has improved vulnerability detection, and recent datasets have reduced label noise and unrelated code changes. However, most existing approaches still operate at the function level, where models are asked to…