CVE-2025-69430

An Incorrect Symlink Follow vulnerability exists in multiple Yottamaster NAS devices, including DM2 version equal to or prior to V1.9.12, DM3 version equal to or prior to V1.9.12, and DM200 version equal to or prior to V1.2.23 that could be exploited by attackers to leak or tamper with the intern...

SAMSUNG多款产品 安全漏洞

SAMSUNG Mobile Processor and SAMSUNG Wearable Processor are both products of South Korean company Samsung. The SAMSUNG Mobile Processor is a series of mobile processors. The SAMSUNG Wearable Processor is a series of wearable processors. Several SAMSUNG products have security vulnerabilities. Thes...

Lexmark 安全漏洞

Lexmark is a series of printers produced by the American company Lexmark. Several Lexmark products have security vulnerabilities, which stem from relative path traversal in the embedded solution framework, potentially allowing for the execution of arbitrary code. The following products are...

CVE-2025-58340

CVE-2025-58340 affects Samsung’s Wi‑Fi driver for the Exynos family (980/850/1080/1280/1330/1380/1480/1580, W920/W930/W1000). The issue is an unbounded memory allocation caused by a large buffer in a /proc/driver/unifi0/send_delts write operation, leading to kernel memory exhaustion. The NVD/Red ...

SAMSUNG多款产品 安全漏洞

SAMSUNG Mobile Processor and SAMSUNG Wearable Processor are both products of South Korean company Samsung. The SAMSUNG Mobile Processor is a series of mobile processors. The SAMSUNG Wearable Processor is a series of wearable processors. Several Samsung products have security vulnerabilities. Thes...

Insertion of Sensitive Information into Log File

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Insertion of Sensitive Information into Log File via the videourl parameter, which allows remote files to be fetched and processed. An attacker can...

CVE-2026-1778 TLS disabled by default in select aws/sagemaker-python-sdk configurations

Amazon SageMaker Python SDK before v3.1.1 or v2.256.0 disables TLS certificate verification for HTTPS connections made by the service when a Triton Python model is imported, incorrectly allowing for requests with invalid and self-signed certificates to succeed...

The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying sleeper agent-style backdoors in causal language models. Our approach relies on two key findings: first, sleeper agents tend to memorize poisoning dat...

Amazon SageMaker Python SDK 安全漏洞

Amazon SageMaker Python SDK is a development toolkit provided by Amazon, Inc., for building, training, and deploying machine learning models. Versions of the Amazon SageMaker Python SDK prior to v3.1.1 and v2.256.0 contained security vulnerabilities. These vulnerabilities stemmed from the disabli...

PT-2026-5709

Name of the Vulnerable Software and Affected Versions Amazon SageMaker Python SDK versions prior to 3.1.1 Amazon SageMaker Python SDK versions prior to 2.256.0 Description The SageMaker Python SDK has an issue where TLS certificate verification is disabled for HTTPS connections when importing a...

Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents

Large language models LLMs have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of experience reuse. We propose Co-RedTeam, a security-aware...

Toxic_Flow_Analysis_Framework_For_Agentic_AI

Toxic Flow Analysis TFA Framework A Secure-by-Design framew...

Iran-Linked RedKitten Cyber Campaign Targets Human Rights NGOs and Activists

A Farsi-speaking threat actor aligned with Iranian state interests is suspected to be behind a new campaign targeting non-governmental organizations and individuals involved in documenting recent human rights abuses. The activity, observed by HarfangLab in January 2026, has been codenamed...

Jailbreaking LLMs Via Calibration

Safety alignment in Large Language Models LLMs often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on next-token prediction is modeled as a systematic distortion of...

From Detection to Prevention: Explaining Security-Critical Code to Avoid Vulnerabilities

Security vulnerabilities often arise unintentionally during development due to a lack of security expertise and code complexity. Traditional tools, such as static and dynamic analysis, detect vulnerabilities only after they are introduced in code, leading to costly remediation. This work explores...

No More, No Less: Least-Privilege Language Models

Least privilege is a core security principle: grant each request only the minimum access needed to achieve its goal. Deployed language models almost never follow it, instead being exposed through a single API endpoint that serves all users and requests. This gap exists not because least privilege...

Okara: Detection and Attribution of TLS Man-In-The-Middle Vulnerabilities in Android Apps with Foundation Models

Transport Layer Security TLS is fundamental to secure online communication, yet vulnerabilities in certificate validation that enable Man-in-the-Middle MitM attacks remain a pervasive threat in Android apps. Existing detection tools are hampered by low-coverage UI interaction, costly...

Evaluating Large Language Models for Security Bug Report Prediction

Early detection of security bug reports SBRs is critical for timely vulnerability mitigation. We present an evaluation of prompt-based engineering and fine-tuning approaches for predicting SBRs using Large Language Models LLMs. Our findings reveal a distinct trade-off between the two approaches...

Semantic-Aware Advanced Persistent Threat Detection Using Autoencoders on LLM-Encoded System Logs

Advanced Persistent Threats APTs are among the most challenging cyberattacks to detect. They are carried out by highly skilled attackers who carefully study their targets and operate in a stealthy, long-term manner. Because APTs exhibit "low-and-slow" behavior, traditional statistical methods and...

The Semantic Trap: Do Fine-Tuned LLMs Learn Vulnerability Root Cause or Just Functional Pattern?

LLMs demonstrate promising performance in software vulnerability detection after fine-tuning. However, it remains unclear whether these gains reflect a genuine understanding of vulnerability root causes or merely an exploitation of functional patterns. In this paper, we identify a critical failur...