Token-Efficient Prompt Injection Attack: Provoking Cessation in LLM Reasoning Via Adaptive Token Compression

While reasoning large language models LLMs demonstrate remarkable performance across various tasks, they also contain notable security vulnerabilities. Recent research has uncovered a "thinking-stopped" vulnerability in DeepSeek-R1, where model-generated reasoning tokens can forcibly interrupt th...

Data Encryption Battlefield: a Deep Dive into the Dynamic Confrontations in Ransomware Attacks

In the rapidly evolving landscape of cybersecurity threats, ransomware represents a significant challenge. Attackers increasingly employ sophisticated encryption methods, such as entropy reduction through Base64 encoding, and partial or intermittent encryption to evade traditional detection...

Memory Allocation with Excessive Size Value

Overview org.jruby:jruby-stdlib is a JRuby Lib Setup package. Affected versions of this package are vulnerable to Memory Allocation with Excessive Size Value in the ResponseReader class. An attacker can cause the application to allocate excessive memory and trigger a denial of service by includin...

undertow: OutOfMemoryError due to @MultipartConfig handling

A flaw was found in undertow. Servlets annotated with @MultipartConfig may cause an OutOfMemoryError due to large multipart content. This may allow unauthorized users to cause remote Denial of Service DoS attack. If the server uses fileSizeThreshold to limit the file size, it's possible to bypass...

undertow: Large AJP request may cause DoS

A flaw was found in Undertow. AJP requests to the server may allow an attacker to send a malicious request and trigger server errors, resulting in a denial of service...

CVE-2025-46656

python-markdownify aka markdownify before 0.14.1 allows large headline prefixes such as in addition to through . This causes memory consumption...

Phishing URL Detection Using Bi-LSTM

Phishing attacks threaten online users, often leading to data breaches, financial losses, and identity theft. Traditional phishing detection systems struggle with high false positive rates and are usually limited by the types of attacks they can identify. This paper proposes a deep learning-based...

Leveraging LLM to Strengthen ML-Based Cross-Site Scripting Detection

According to the Open Web Application Security Project OWASP, Cross-Site Scripting XSS is a critical security vulnerability. Despite decades of research, XSS remains among the top 10 security vulnerabilities. Researchers have proposed various techniques to protect systems from XSS attacks, with...

Hybrid Privacy Policy-Code Consistency Check Using Knowledge Graphs and LLMs

The increasing concern in user privacy misuse has accelerated research into checking consistencies between smartphone apps' declared privacy policies and their actual behaviors. Recent advances in Large Language Models LLMs have introduced promising techniques for semantic comparison, but these...

dify 安全漏洞

dify is an open source LLM application development platform from LangGenius Open Source. A security vulnerability exists in versions of dify prior to 1.3.0, which stems from a clickjacking vulnerability in the default settings that could lead to unauthorized operations...

SAGE: a Generic Framework for LLM Safety Evaluation

Whitepaper called SAGE: A Generic Framework For LLM Safety Evaluation...

GHSA-7MPR-5M44-H73R markdownify allows large headline prefixes such as <h9999999>, which causes memory consumption

python-markdownify aka markdownify before 0.14.1 allows large headline prefixes such as in addition to through . This causes memory consumption...

CVE-2025-46656

python-markdownify aka markdownify before 0.14.1 allows large headline prefixes such as in addition to through . This causes memory consumption...

CVE-2025-32952

Jmix is a set of libraries and tools to speed up Spring Boot data-centric application development. In versions 1.0.0 to 1.6.1 and 2.0.0 to 2.3.4, the local file storage implementation does not restrict the size of uploaded files. An attacker could exploit this by uploading excessively large files...

PT-2025-17965

Name of the Vulnerable Software and Affected Versions python-markdownify aka markdownify versions prior to 0.14.1 Description The issue allows large headline prefixes, such as , in addition to the standard through tags. This can cause excessive memory consumption. Recommendations For versions pri...

CVE-2025-46656

python-markdownify aka markdownify before 0.14.1 allows large headline prefixes such as in addition to through . This causes memory consumption...

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges

Large language models LLMs have demonstrated remarkable capabilities, especially the recent advancements in reasoning, such as o1 and o3, pushing the boundaries of AI. Despite these impressive achievements in mathematics and coding, the reasoning abilities of LLMs in domains requiring cryptograph...

The Dark Side of the Web: Towards Understanding Various Data Sources in Cyber Threat Intelligence

Cyber threats have become increasingly prevalent and sophisticated. Prior work has extracted actionable cyber threat intelligence CTI, such as indicators of compromise, tactics, techniques, and procedures TTPs, or threat feeds from various sources: open source data e.g., social networks, internal...

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

The challenge of ensuring Large Language Models LLMs align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against su...

A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection

Phishing attacks represent an increasingly sophisticated and pervasive threat to individuals and organizations, causing significant financial losses, identity theft, and severe damage to institutional reputations. Existing phishing detection methods often struggle to simultaneously achieve high...