Malicious ML Models on Hugging Face Leverage Broken Pickle Format to Evade Detection

Cybersecurity researchers have uncovered two malicious machine learning ML models on Hugging Face that leveraged an unusual technique of "broken" pickle files to evade detection. "The pickle files extracted from the mentioned PyTorch archives revealed the malicious Python content at the beginning...

Why Cybercriminals Are Not Necessarily Embracing AI

As published in HackerNoon and featured as a “Top 20 Best Read Article” for AI. Introduction The rapid advancement of AI has offered powerful tools for malware detection, but it has also introduced new avenues for adversarial attacks. As an example, recently OpenAI reported threat actors abusing...

The vulnerability of the library for optimizing machine learning models in Intel Neural Compressor allows attackers to exploit it by bypassing security measures related to SQL query structures, thereby enabling them to enhance their privileges.

The vulnerability of the Intel Neural Compressor library for optimizing machine learning models is related to the lack of protective measures for SQL query structures. Exploiting this vulnerability can allow attackers to enhance their privileges remotely...

Division By Zero Error

TensorFlow is vulnerable to a division by zero error. The vulnerability is due to insufficient handling of cases where the input's fourth dimension is zero in the DepthwiseConv TFLite operator, which can allows to execution issues or crashes in machine learning models...

Unpacking 2024's SaaS Threat Predictions

Early in 2024, Wing Security released its State of SaaS Security report, offering surprising insights into emerging threats and best practices in the SaaS domain. Now, halfway through the year, several SaaS threat predictions from the report have already proven accurate. Fortunately, SaaS Securit...

CVE-2024-34359

CVE-2024-34359 affects llama-cpp-python (Python bindings for llama.cpp). The vulnerability arises when init loads a model’s chat template from the gguf metadata and constructs self.chat_handler via llama_chat_format.Jinja2ChatFormatter.to_chat_handler(), using a sandbox-less Jinja2 Environment. R...

How to keep your ChatGPT conversations out of its training data

Last week, OpenAI announced it had given ChatGPT users the option to turn off their chat history. ChatGPT is a "generative AI", a machine learning algorithm that can understand language and generate written responses. Users can interact with it by asking questions, and the conversations users hav...

Google Cloud Introduces Security AI Workbench for Faster Threat Detection and Analysis

Google's cloud division is following in the footsteps of Microsoft with the launch of Security AI Workbench that leverages generative AI models to gain better visibility into the threat landscape. Powering the cybersecurity suite is Sec-PaLM, a specialized large language model LLM that's...

Attack AI systems in Machine Learning Evasion Competition

Today, we are launching MLSEC.IO, an educational Machine Learning Security Evasion Competition MLSEC for the AI and security communities to exercise their muscle to attack critical AI systems in a realistic setting. Hosted and sponsored by Microsoft, alongside NVIDIA, CUJO AI, VM-Ray, and MRG...

Do CAPTCHAs work and what’s the alternative?

We know youre busy, so the answer is “No”. Users want less friction, and a good bot detection and mitigation solution will do the job MUCH better. The first lesson on the first day of UI school is that users want the path of least resistance. While the gamification of cybersecurity does have a...

6 strategies to reduce cybersecurity alert fatigue in your SOC

Today, organizations are faced with the increasingly difficult task of trying to protect their expanding digital estate from sophisticated cybersecurity threats. Migration to the cloud and a mobile workforce has dissolved the network boundary and projected the digital estate beyond its traditiona...

SoReL-20M: A Huge Dataset of 20 Million Malware Samples Released Online

Cybersecurity firms Sophos and ReversingLabs on Monday jointly released the first-ever production-scale malware research dataset to be made available to the general public that aims to build effective defenses and drive industry-wide improvements in security detection and response. "SoReL-20M"...

Confusing Self-Driving Cars by Altering Road Signs

Researchers found that they could confuse the road sign detection algorithms of self-driving cars by adding stickers to the signs on the road. They could, for example, cause a car to think that a stop sign is a 45 mph speed limit sign. The changes are subtle, though -- look at the photo from the...

Tech support scams persist with increasingly crafty techniques

Note: Our Tech support scams FAQ page has the latest info on this type of threat, including scammer tactics, fake error messages, and the latest scammer hotlines. You can also read our latest blog, New tech support scam launches communication or phone call app. Millions of users continue to...