Enhancing Targeted Adversarial Attacks on Large Vision-Language Models through Intermediate Projector Guidance

Targeted adversarial attacks are essential for proactively identifying security flaws in Vision-Language Models before real-world deployment. However, current methods perturb images to maximize global similarity with the target text or reference image at the encoder level, collapsing rich visual...

Zero Trust + AI: Privacy in the Age of Agentic AI

We used to think of privacy as a perimeter problem: about walls and locks, permissions, and policies. But in a world where artificial agents are becoming autonomous actors — interacting with data, systems, and humans without constant oversight — privacy is no longer about control. It's about trus...

Linux Distros Unpatched Vulnerability : CVE-2025-22049

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: LoongArch: Increase ARCHDMAMINALIGN up to 16 ARCHDMAMINALIGN is 1 by default, but some...

Linux Distros Unpatched Vulnerability : CVE-2022-50075

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: tracing/eprobes: Have event probes be consistent with kprobes and uprobes Currently, if a...

Amazon Nova AI Challenge -- Trusted AI: Advancing Secure, AI-Assisted Software Development

AI systems for software development are rapidly gaining prominence, yet significant challenges remain in ensuring their safety. To address this, Amazon launched the Trusted AI track of the Amazon Nova AI Challenge, a global competition among 10 university teams to drive advances in secure AI. In...

CLSA-2025-1755003990 libvpx: Fix of CVE-2024-5197

CVE-2024-5197: fix integer overflows in image allocation and wrapping logic, validate dimensions and alignment to prevent invalid buffer calculations...

Linux Distros Unpatched Vulnerability : CVE-2022-50182

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: media: imx-jpeg: Align upwards buffer size The hardware can support any image size WxH, with...

Linux Distros Unpatched Vulnerability : CVE-2025-21851

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: bpf: Fix softlockup in arenamapfree on 64k page kernel On an aarch64 kernel with...

6 Lessons Learned: Focusing Security Where Business Value Lives

The Evolution of Exposure Management Most security teams have a good sense of what's critical in their environment. What's harder to pin down is what's business-critical. These are the assets that support the processes the business can't function without. They're not always the loudest or most...

Linux Distros Unpatched Vulnerability : CVE-2025-22033

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: arm64: Don't call NULL in docompatalignmentfixup doalignmentt32tohandler only fixes up...

Linux Distros Unpatched Vulnerability : CVE-2024-26998

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: serial: core: Clearing the circular buffer before NULLifying it The circular buffer is...

Linux Distros Unpatched Vulnerability : CVE-2025-37922

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: book3s64/radix : Align section vmemmap start address to PAGESIZE A vmemmap altmap is a...

Linux Distros Unpatched Vulnerability : CVE-2024-53225

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: iommu/tegra241-cmdqv: Fix alignment failure at maxnshift When configuring a kernel with...

Linux Distros Unpatched Vulnerability : CVE-2024-56560

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: slab: Fix too strict alignment check in createcache On m68k, where the minimum alignment of...

Linux Distros Unpatched Vulnerability : CVE-2024-43868

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - In the Linux kernel, the following vulnerability has been resolved: riscv/purgatory: align riscvkernelentry When alignment handling is delegated to the kernel,...

kernel: ext4: avoid resizing to a partial cluster size

In the Linux kernel, the following vulnerability has been resolved: ext4: avoid resizing to a partial cluster size This patch avoids an attempt to resize the filesystem to an unaligned cluster boundary. An online resize to a size that is not integral to cluster size results in the last iteration...

Large Reasoning Models Are Autonomous Jailbreak Agents

Jailbreaking -- bypassing built-in safety mechanisms in AI models -- has traditionally required complex technical procedures or specialized human expertise. In this study, we show that the persuasive capabilities of large reasoning models LRMs simplify and scale jailbreaking, converting it into a...

Secure Wireless Communication Via Polarforming

Polarforming is a promising technique that enables dynamic adjustment of antenna polarization to mitigate depolarization effects commonly encountered during electromagnetic EM wave propagation. In this letter, we investigate the polarforming design for secure wireless communication systems, where...

PT-2025-35961

Name of the Vulnerable Software and Affected Versions Linux kernel affected versions not specified Description The Linux kernel contains a flaw in the iommufd subsystem where an integer overflow can occur during IOVA allocation due to an incorrect alignment calculation using the ALIGN function...

PRM-Free Security Alignment of Large Models Via Red Teaming and Adversarial Training

Large Language Models LLMs have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies predominantly rely on Process Reward Models PRMs to evaluate...