AutoRAN: Weak-To-Strong Jailbreaking of Large Reasoning Models

This paper presents AutoRAN, the first automated, weak-to-strong jailbreak attack framework targeting large reasoning models LRMs. At its core, AutoRAN leverages a weak, less-aligned reasoning model to simulate the target model's high-level reasoning structures, generates narrative prompts, and...

MPMA: Preference Manipulation Attack against Model Context Protocol

Model Context Protocol MCP standardizes interface mapping for large language models LLMs to access external data and tools, which revolutionizes the paradigm of tool selection and facilitates the rapid expansion of the LLM agent tool ecosystem. However, as the MCP is increasingly adopted,...

GenoArmory: a Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

We propose the first unified adversarial attack benchmark for Genomic Foundation Models GFMs, named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologicall...

CVE-2025-4701 VITA-MLLM Freeze-Omni utils.py torch.load deserialization

A vulnerability, which was classified as problematic, has been found in VITA-MLLM Freeze-Omni up to 20250421. This issue affects the function torch.load of the file models/utils.py. The manipulation of the argument path leads to deserialization. It is possible to launch the attack on the local ho...

Developer Leaks API Key for Private Tesla, SpaceX LLMs

In AI, as with so many advancing technologies, security often lags innovation. The xAI incident, during which a sensitive API key remained exposed for nearly two months, is a stark reminder of this disconnect. Such oversights not only jeopardize proprietary technologies but also highlight systemi...

Freeze-Omni 代码问题漏洞

Freeze-Omni is an intelligent low-latency speech dialog model based on Freeze LLM open-sourced by VITA-MLLM. A code issue vulnerability exists in Freeze-Omni 20250421 and earlier versions, which stems from deserialization due to incorrect manipulation of the parameter path in the file...

Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy

Large Language Models LLMs have gained significant popularity due to their remarkable capabilities in text understanding and generation. However, despite their widespread deployment in inference services such as ChatGPT, concerns about the potential leakage of sensitive user data have arisen...

Dark LLMs: the Growing Threat of Unaligned AI Models

Large Language Models LLMs rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to jailbreaking. The fundamental vulnerability of LLMs to jailbreak...

PT-2025-21290 · Unknown +1 · Vita-Mllm Freeze-Omni +1

Name of the Vulnerable Software and Affected Versions: VITA-MLLM Freeze-Omni up to 20250421 Description: A problematic issue has been found, affecting the torch.load function in the models/utils.py file. The manipulation of the path argument leads to deserialization, allowing an attack to be...

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

The integration of large language models LLMs into cyber security applications presents significant opportunities, such as enhancing threat analysis and malware detection, but can also introduce critical risks and safety concerns, including personal data leakage and automated generation of new...

CVE-2025-4701: Deserialization of Untrusted Data

A vulnerability, which was classified as problematic, has been found in VITA-MLLM Freeze-Omni up to 20250421. This issue affects the function torch.load of the file models/utils.py. The manipulation of the argument path leads to deserialization. It is possible to launch the attack on the local ho...

On Technique Identification and Threat-Actor Attribution Using LLMs and Embedding Models

Attribution of cyber-attacks remains a complex but critical challenge for cyber defenders. Currently, manual extraction of behavioral indicators from dense forensic documentation causes significant attribution delays, especially following major incidents at the international scale. This research...

SafeTrans: LLM-Assisted Transpilation from C to Rust

Rust is a strong contender for a memory-safe alternative to C as a "systems" programming language, but porting the vast amount of existing C code to Rust is a daunting task. In this paper, we evaluate the potential of large language models LLMs to automate the transpilation of C code to idiomatic...

Private Transformer Inference in MLaaS: a Survey

Transformer models have revolutionized AI, powering applications like content generation and sentiment analysis. However, their deployment in Machine Learning as a Service MLaaS raises significant privacy concerns, primarily due to the centralized processing of sensitive user data. Private...

S3C2 Summit 2024-09: Industry Secure Software Supply Chain Summit

While providing economic and software development value, software supply chains are only as strong as their weakest link. Over the past several years, there has been an exponential increase in cyberattacks, specifically targeting vulnerable links in critical software supply chains. These attacks...

Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

As Large Language Models LLMs are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from human feedback RLHF, they are still vulnerable to jailbreakin...

Palo Alto Networks PAN-OS 10.1.x < 10.1.14-h14 / 10.2.x < 10.2.11 / 11.0.x < 11.0.7 / 11.1.x < 11.1.5 Vulnerability

The version of Palo Alto Networks PAN-OS running on the remote host is 10.1.x prior to 10.1.14-h14, 10.2.x prior to 10.2.11, 11.0.x prior to 11.0.7, or 11.1.x prior to 11.1.5. It is, therefore, affected by a vulnerability. Using the AES-128-CCM algorithm for IPSec on certain Palo Alto Networks...

D-Link Firewall Service Code Execution

The vulnerability of the Firewall Service component in D-Link’s DIR-618 and DIR-605L router microprogramming systems is related to access control errors. Exploiting this vulnerability allows a remote attacker to execute arbitrary code...

RUGGEDCOM ROX Traceroute Code Execution

The vulnerability of the traceroute utility in the microprogramming-based routing and switching platform RUGGEDCOM ROX for series MX MX5000, MX5000RE and RX RX1400, RX1501, RX1510, RX1511, RX1512, RX1524, RX1536, and RX5000 lies in the absence of a mechanism to verify input data on the server sid...

CVE-2025-31929

A vulnerability has been identified in IEC 1Ph 7.4kW Child socket 8EM1310-2EH04-0GA0 All versions, IEC 1Ph 7.4kW Child socket/ shutter 8EM1310-2EN04-0GA0 All versions, IEC 1Ph 7.4kW Parent cable 7m 8EM1310-2EJ04-3GA1 All versions, IEC 1Ph 7.4kW Parent cable 7m incl. SIM 8EM1310-2EJ04-3GA2 All...