ObfusBFA: a Holistic Approach to Safeguarding DNNs from Different Types of Bit-Flip Attacks

Bit-flip attacks BFAs represent a serious threat to Deep Neural Networks DNNs, where flipping a small number of bits in the model parameters or binary code can significantly degrade the model accuracy or mislead the model prediction in a desired way. Existing defenses exclusively focus on...

Cyber Security of Sensor Systems for State Sequence Estimation: an AI Approach

Sensor systems are extremely popular today and vulnerable to sensor data attacks. Due to possible devastating consequences, counteracting sensor data attacks is an extremely important topic, which has not seen sufficient study. This paper develops the first methods that accurately...

CVE-2025-48990 NeKernel has Heap Overflow in `rt_copy_memory`

NeKernal is a free and open-source operating system stack. Version 0.0.2 has a 1-byte heap overflow in rtcopymemory, which unconditionally wrote a null terminator at dstlen. When len equals the size of the destination buffer 256 bytes, that extra '\0' write overruns the buffer by one byte. To avo...

A Geometric Square-Based Approach to RSA Integer Factorization

We present a new approach to RSA factorization inspired by geometric interpretations and square differences. This method reformulates the problem in terms of the distance between perfect squares and provides a recurrence relation that allows rapid convergence when the RSA modulus has closely spac...

Privacy-Aware, Public-Aligned: Embedding Risk Detection and Public Values into Scalable Clinical Text De-Identification for Trusted Research Environments

Clinical free-text data offers immense potential to improve population health research such as richer phenotyping, symptom tracking, and contextual understanding of patient care. However, these data present significant privacy risks due to the presence of directly or indirectly identifying...

GHSA-4QJH-9FV9-R85R Potential Timing Side-Channel Vulnerability in vLLM’s Chunk-Based Prefix Caching

This issue arises from the prefix caching mechanism, which may expose the system to a timing side-channel attack. Description When a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT Time to First...

Semantic-Preserving Adversarial Attacks on LLMs: an Adaptive Greedy Binary Search Approach

Large Language Models LLMs increasingly rely on automatic prompt engineering in graphical user interfaces GUIs to refine user inputs and enhance response accuracy. However, the diversity of user requirements often leads to unintended misinterpretations, where automated optimizations distort...

CVE-2020-8815

Improper connection handling in the base connection handler in IKTeam BearFTP before v0.3.1 allows a remote attacker to achieve denial of service via a Slowloris approach by sending a large volume of small packets...

Deloitte’s Secure by Design (SbD) Approach – Enhanced with Wiz

How Deloitte and Wiz Enable End-to-End Security Without Slowing Down Development...

Breaking the Sound Barrier Part I: Fuzzing CoreAudio with Mach Messages

Guest post by Dillon Franke, Senior Security Engineer, 20% time on Project Zero Every second, highly-privileged MacOS system daemons accept and process hundreds of IPC messages. In some cases, these message handlers accept data from sandboxed or unprivileged processes. In this blog post, I’ll...

PT-2025-19712

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description The issue concerns the Linux kernel's bpf Berkeley Packet Filter functionality. Specifically, it involves tail calls that can invalidate packet pointers, potentially allowing tail-called...

LLM Watermarking Using Mixtures and Statistical-To-Computational Gaps

Given a text, can we determine whether it was generated by a large language model LLM or by a human? A widely studied approach to this problem is watermarking. We propose an undetectable and elementary watermarking scheme in the closed setting. Also, in the harder open setting, where the adversar...

Applying Security Engineering to Prompt Injection Security

This seems like an important advance in LLM security against prompt injection: Google DeepMind has unveiled CaMeL CApabilities for MachinE Learning, a new approach to stopping prompt-injection attacks that abandons the failed strategy of having AI models police themselves. Instead, CaMeL treats...

⚡ Weekly Recap: Critical SAP Exploit, AI-Powered Phishing, Major Breaches, New CVEs & More

What happens when cybercriminals no longer need deep skills to breach your defenses? Today's attackers are armed with powerful tools that do the heavy lifting — from AI-powered phishing kits to large botnets ready to strike. And they're not just after big corporations. Anyone can be a target when...

​​Explore practical best practices to secure your data with Microsoft Purview​​

According to the Microsoft 2024 Data Security Index, organizations experience an average of 156 data security incidents annually, and this cyberthreat continues to be a top concern for data security decision-makers.1 A full 82% of security decision-makers believe a comprehensive, fully integrated...

​​Explore practical best practices to secure your data with Microsoft Purview​​

According to the Microsoft 2024 Data Security Index, organizations experience an average of 156 data security incidents annually, and this cyberthreat continues to be a top concern for data security decision-makers.1 A full 82% of security decision-makers believe a comprehensive, fully integrated...

A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content

Large Language Models LLM have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel approach focuses on a post-generation correction mechanism...

Webinar: Learn How ASPM Transforms Application Security from Reactive to Proactive

Are you tired of dealing with outdated security tools that never seem to give you the full picture? You're not alone. Many organizations struggle with piecing together scattered information, leaving your apps vulnerable to modern threats. That's why we're excited to introduce a smarter, unified...

The Role of Runtime Security in Cloud Environments

Discover how Wiz's innovative hybrid approach revolutionizes runtime security for the modern cloud era...

ICS testing best results. Hint: Blend your approach

TL;DR Onsite ICS testing is risk averse Laboratory ICS device testing uncovers more A blended approach is key How that works Demonstrable benefits Introduction For safety’s sake onsite ICS testing adopts a risk averse approach, even if scheduled during downtime or a maintenance period. It’s vital...