SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning

Large Reasoning Models LRMs introduce a new generation paradigm of explicitly reasoning before answering, leading to remarkable improvements in complex tasks. However, they pose great safety risks against harmful queries and adversarial attacks. While recent mainstream safety efforts on LRMs,...

Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: an Empirical Study on Popular Open-Source Projects

Command injection vulnerabilities are a significant security threat in dynamic languages like Python, particularly in widely used open-source projects where security issues can have extensive impact. With the proven effectiveness of Large Language ModelsLLMs in code-related tasks, such as testing...

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study

Rapid deployment of vision-language models VLMs magnifies safety risks, yet most evaluations rely on artificial images. This study asks: How safe are current VLMs when confronted with meme images that ordinary users share? To investigate this question, we introduce MemeSafetyBench, a...

FragFake: a Dataset for Fine-Grained Detection of Edited Images with Vision Language Models

Fine-grained edited image detection of localized edits in images is crucial for assessing content authenticity, especially given that modern diffusion models and image editing methods can produce highly realistic manipulations. However, this domain faces three challenges: 1 Binary classifiers yie...

The vulnerability of the administrator panel of microprogrammed software routers such as GL-A1300, GL-AX1800, GL-AXT1800, GL-MT3000, GL-MT2500, GL-MT6000, GL-MT1300, GL-MT300N-V2, GL-AR750S, GL-AR750, GL-AR300M, and GL-B1300 allows attackers to circumvent security restrictions, gain increased privileges, and obtain full control over the device.

The vulnerability of the administrator panel of microprogrammed software routers such as GL-A1300, GL-AX1800, GL-AXT1800, GL-MT3000, GL-MT2500, GL-MT6000, GL-MT1300, GL-MT300N-V2, GL-AR750S, GL-AR750, GL-AR300M, and GL-B1300 is related to deficiencies in authentication procedures. Exploiting this...

FedGraM: Defending against Untargeted Attacks in Federated Learning Via Embedding Gram Matrix

Federated Learning FL enables geographically distributed clients to collaboratively train machine learning models by sharing only their local models, ensuring data privacy. However, FL is vulnerable to untargeted attacks that aim to degrade the global model's performance on the underlying data...

AudioJailbreak: Jailbreak Attacks against End-To-End Large Audio-Language Models

Jailbreak attacks to Large audio-language models LALMs are studied recently, but they achieve suboptimal effectiveness, applicability, and practicability, particularly, assuming that the adversary can fully manipulate user prompts. In this work, we first conduct an extensive experiment showing th...

Training-Free Watermarking for Autoregressive Image Generation

Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for autoregressive image generation models remains largely underexplored...

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents

The growing adoption of large language models LLMs has led to a new paradigm in mobile computing--LLM-powered mobile AI agents--capable of decomposing and automating complex tasks directly on smartphones. However, the security implications of these agents remain largely unexplored. In this paper,...

JULI: Jailbreak Large Language Models by Self-Introspection

Large Language Models LLMs are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as necessitating access to the model weights or the generation process...

Is Your Prompt Safe? Investigating Prompt Injection Attacks against Open-Source LLMs

Whitepaper called Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs...

Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMs

In the age of cloud computing, data privacy protection has become a major challenge, especially when sharing sensitive data across cloud environments. However, how to optimize collaboration across cloud environments remains an unresolved problem. In this paper, we combine federated learning with...

MorphMark: Flexible Adaptive Watermarking for Large Language Models

Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models LLMs. However, existing watermark methods often struggle with a fundamental dilemma: improving watermark effectiveness the...

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems

Large Language Models LLMs enhanced with Retrieval-Augmented Generation RAG have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly...

Fragments to Facts: Partial-Information Fragment Inference from LLMs

Large language models LLMs can leak sensitive training data through memorization and membership inference attacks. Prior work has primarily focused on strong adversarial assumptions, including attacker access to entire samples or long, ordered prefixes, leaving open the question of how vulnerable...

R1dacted: Investigating Local Censorship in DeepSeek'S R1 Language Model

DeepSeek recently released R1, a high-performing large language model LLM optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performance, even surpassing leading reasoning models like OpenAI's o1 on several benchmarks. However, emerging reports suggest...

On Membership Inference Attacks in Knowledge Distillation

Nowadays, Large Language Models LLMs are trained on huge datasets, some including sensitive information. This poses a serious privacy concern because privacy attacks such as Membership Inference Attacks MIAs may detect this sensitive information. While knowledge distillation compresses LLMs into...

TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text

Accurately identifying adversarial techniques in security texts is critical for effective cyber defense. However, existing methods face a fundamental trade-off: they either rely on generic models with limited domain precision or require resource-intensive pipelines that depend on large labeled...

Benchmarking LLMs in an Embodied Environment for Blue Team Threat Hunting

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models LLMs offer promising capabilities for enhancing threat analysis. However, their effectiveness in real-world blue...

FABLE: a Localized, Targeted Adversarial Attack on Weather Forecasting Models

Deep learning-based weather forecasting models have recently demonstrated significant performance improvements over gold-standard physics-based simulation tools. However, these models are vulnerable to adversarial attacks, which raises concerns about their trustworthiness. In this paper, we first...