Anthropic Claims Chinese AI Firms ‘Distilled’ Claude to Train Their Models

Anthropic claims Chinese AI firms distilled Claude to train rival AI models, raising concerns about model extraction, security risks, and AI distillation abuse...

AdapTools: Adaptive Tool-Based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services e.g., Model Context Protocol, MCP has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection IPI attacks...

Analysis of LLMs against Prompt Injection and Jailbreak Attacks

Large Language Models LLMs are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus,...

📄 GrandStream GXP1600 Unauthenticated Remote Code Execution

An unauthenticated stack-based buffer overflow vulnerability exists in the HTTP API endpoint /cgi-bin/api.values.get. A remote attacker can leverage this vulnerability to achieve unauthenticated remote code execution RCE with root privileges on a target device. The vulnerability affects all six...

SafePickle: Robust and Generic ML Detection of Malicious Pickle-Based ML Models

Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution RCE risks during model loading. Recent defenses, such as PickleBall, rely on per-library policy synthesis that requires comple...

An Explainable Memory Forensics Approach for Malware Analysis

Memory forensics is an effective methodology for analyzing living-off-the-land malware, including threats that employ evasion, obfuscation, anti-analysis, and steganographic techniques. By capturing volatile system state, memory analysis enables the recovery of transient artifacts such as decrypt...

LLM-Enabled Applications Require System-Level Threat Monitoring

LLM-enabled applications are rapidly reshaping the software ecosystem by using large language models as core reasoning components for complex task execution. This paradigm shift, however, introduces fundamentally new reliability challenges and significantly expands the security attack surface, du...

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the securit...

CVE-2026-20137

In Splunk Enterprise versions below 10.2.0, 10.0.3, 9.4.5, 9.3.7, and 9.2.9, and Splunk Cloud Platform versions below 10.1.2507.0, 10.0.2503.9, 9.3.2411.112, and 9.3.2408.122, a low-privileged user who does not hold the "admin" or "power" Splunk roles could bypass the SPL safeguards for risky...

TFL: Targeted Bit-Flip Attack on Large Language Model

Large language models LLMs are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks BFAs, which exploit computer main memory i.e., DRAM vulnerabilitie...

Would You Click ‘Accept’? Automatically detecting malicious Azure OAuth applications using LLMs

How Wiz Research automates detection of emerging malicious Azure app and consent phishing campaigns...

Recursive Language Models for Jailbreak Detection: A Procedural Defense for Tool-Augmented Agents

Jailbreak prompts are a practical and evolving threat to large language models LLMs, particularly in agentic systems that execute tools over untrusted content. Many attacks exploit long-context hiding, semantic camouflage, and lightweight obfuscations that can evade single-pass guardrails. We...

Mind the Gap: Evaluating LLMs for High-Level Malicious Package Detection Vs. Fine-Grained Indicator Identification

The prevalence of malicious packages in open-source repositories, such as PyPI, poses a critical threat to the software supply chain. While Large Language Models LLMs have emerged as a promising tool for automated security tasks, their effectiveness in detecting malicious packages and indicators...

PT-2026-20432

Name of the Vulnerable Software and Affected Versions: Grandstream GXP1610, GXP1615, GXP1620, GXP1625, GXP1628, and GXP1630 versions prior to 1.0.7.81. Description: A critical unauthenticated stack-based buffer overflow vulnerability exists in the HTTP API endpoint /cgi-bin/api.values.get. This...

Discovering Universal Activation Directions for PII Leakage in Language Models

Modern language models exhibit rich internal structure, yet little is known about how privacy-sensitive behaviors, such as personally identifiable information PII leakage, are represented and modulated within their hidden states. We present UniLeak, a mechanistic-interpretability framework that...

Grandstream GXP series 安全漏洞

The Grandstream GXP series is a series of IP phones produced by the American company Grandstream. There are security vulnerabilities in the Grandstream GXP series. These vulnerabilities stem from an unauthenticated, stack-based buffer overflow vulnerability in the /cgi-bin/api.values.get HTTP API...

GrandStream GXP1600 Unauthenticated Remote Code Execution

An unauthenticated stack-based buffer overflow vulnerability exists in the HTTP API endpoint /cgi-bin/api.values.get. A remote attacker can leverage this vulnerability to achieve unauthenticated remote code execution RCE with root privileges on a target device. The vulnerability affects all six...

Side-Channel Attacks Against LLMs

Here are three papers describing different side-channel attacks against LLMs. "Remote Timing Attacks on Efficient Language Model Inference": Abstract: Scaling up language models has significantly increased their capabilities. But larger models are slower models, and so there is now an extensive...

DARTH-PUM: A Hybrid Processing-Using-Memory Architecture

Analog processing-using-memory PUM; a.k.a. in-memory computing makes use of electrical interactions inside memory arrays to perform bulk matrix-vector multiplication MVM operations. However, many popular matrix-based kernels need to execute non-MVM operations, which analog PUM cannot directly...

What Hackers Talk about When They Talk about AI: Early-Stage Diffusion of a Cybercrime Innovation

The rapid expansion of artificial intelligence AI is raising concerns about its potential to transform cybercrime. Beyond empowering novice offenders, AI stands to intensify the scale and sophistication of attacks by seasoned cybercriminals. This paper examines the evolving relationship between...