NegBLEURT Forest: Leveraging Inconsistencies for Detecting Jailbreak Attacks

Jailbreak attacks designed to bypass safety mechanisms pose a serious threat by prompting LLMs to generate harmful or inappropriate content, despite alignment with ethical guidelines. Crafting universal filtering rules remains difficult due to their inherent dependence on specific contexts. To...

Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection

Fairness is a core element in the trustworthy deployment of deepfake detection models, especially in the field of digital identity security. Biases in detection models toward different demographic groups, such as gender and race, may lead to systemic misjudgments, exacerbating the digital divide...

StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models Via Style-Aware Audio Jailbreak

Large Audio-language Models LAMs have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models LLMs. However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio promp...

kernel: bpf: Fix softlockup in arena_map_free on 64k page kernel

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix softlockup in arenamapfree on 64k page kernel On an aarch64 kernel with CONFIGPAGESIZE64KB=y, arenahtab tests cause a segmentation fault and soft lockup. The same failure is not observed with 4k pages on aarch64. It turn...

kernel: bpf: Fix softlockup in arena_map_free on 64k page kernel

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix softlockup in arenamapfree on 64k page kernel On an aarch64 kernel with CONFIGPAGESIZE64KB=y, arenahtab tests cause a segmentation fault and soft lockup. The same failure is not observed with 4k pages on aarch64. It turn...

EASE: Practical and Efficient Safety Alignment for Small Language Models

Small language models SLMs are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While...

Quantifying the Risk of Transferred Black Box Attacks

Neural networks have become pervasive across various applications, including security-related products. However, their widespread adoption has heightened concerns regarding vulnerability to adversarial attacks. With emerging regulations and standards emphasizing security, organizations must...

Unity Linux 20.1070a Security Update: kernel (UTSA-2025-990566)

"The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2025-990566 advisory. In the Linux kernel, the following vulnerability has been resolved: arm64: asm-bug: Add .align 2 to the end of BUGENTRY When CONFIGDEBUGBUGVERBOSE=n, we fail to add...

CVE-2025-61084

MDaemon Mail Server 23.5.2 validates SPF, DKIM, and DMARC using the email enclosed in angle brackets in the From: header of SMTP DATA. An attacker can craft a From: header with multiple invisible Unicode thin spaces to display a spoofed sender while passing validation, allowing email spoofing eve...

Unity Linux 20.1070e Security Update: kernel (UTSA-2025-989849)

"The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2025-989849 advisory. In the Linux kernel, the following vulnerability has been resolved: arm64: asm-bug: Add .align 2 to the end of BUGENTRY When CONFIGDEBUGBUGVERBOSE=n, we fail to add...

Unity Linux 20.1060a / 20.1070a Security Update: kernel (UTSA-2025-989490)

The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2025-989490 advisory. In the Linux kernel, the following vulnerability has been resolved: bpf, testrun: Fix alignment problem in bpfprogtestrunskb We got a syzkaller problem because of...

Machine and Deep Learning for Indoor UWB Jammer Localization

Ultra-wideband UWB localization delivers centimeter-scale accuracy but is vulnerable to jamming attacks, creating security risks for asset tracking and intrusion detection in smart buildings. Although machine learning ML and deep learning DL methods have improved tag localization, localizing...

Astra Linux – Vulnerability in Linux 6.12

In the Linux kernel, the following vulnerability has been resolved: iommufd: Prevents ALIGN overflow. When allocating IOVA, the candidate range is aligned to the target alignment. If the range is close to ULONGMAX, the ALIGN function may wrap, resulting in a corrupted iova structure. The code use...

Astra Linux – Vulnerability in Linux 6.12

In the Linux kernel, the following vulnerability has been resolved: iouring/rsrc: Do not rely on user vaddr alignment. There is no guaranteed alignment for user pointers. However, the calculation of the offset from the first page to a folio after coalescing uses some strange bit mask logic;...

UBUNTU-CVE-2025-40063

In the Linux kernel, the following vulnerability has been resolved: crypto: comp - Use same definition of context alloc and free ops In commit 42d9f6c77479 "crypto: acomp - Move scomp stream allocation code into acomp", the cryptoacompstreams struct was made to rely on having the allocctx and...

Siemens SIMATIC Devices NULL Pointer Dereference (CVE-2023-52458)

In the Linux kernel, the following vulnerability has been resolved: block: add check that partition length needs to be aligned with block size This plugin only works with Tenable.ot. Please visit https://www.tenable.com/products/tenable-ot for more information. %NASLMINLEVEL 80900 C Tenable, Inc...

Linux Distros Unpatched Vulnerability : CVE-2025-39973

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - i40e: add validation for ringlen param The ringlen parameter provided by the virtual function VF is assigned directly to the hardware memory context HMC without...

Secure AI at Scale and Speed — Learn the Framework in this Free Webinar

AI is everywhere—and your company wants in. Faster products, smarter systems, fewer bottlenecks. But if you're in security, that excitement often comes with a sinking feeling. Because while everyone else is racing ahead, you're left trying to manage a growing web of AI agents you didn't create,...

PT-2025-51712

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description The Linux kernel contains a flaw within the kvaser usb leaf wait cmd and kvaser usb leaf read bulk callback functions related to handling zero-length commands used for aligning data to U...

Everyone Needs AIR: An Agnostic Incident Reporting Framework for Cybersecurity in Operational Technology

Operational technology OT networks are increasingly coupled with information technology IT, expanding the attack surface and complicating incident response. Although OT standards emphasise incident reporting and evidence preservation, they do not specify what data to capture during an incident,...