Probing the Robustness of Large Language Models Safety to Latent Perturbations

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We argue that this stems from the shallow nature of existing...

DEBIAN-CVE-2022-50182

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 arbitrary W image width and H image height dimensions. Align upwards buffer size for both encoder and decoder. and leave the picture...

CVE-2022-50182

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 arbitrary W image width and H image height dimensions. Align upwards buffer size for both encoder and decoder. and leave the picture...

UBUNTU-CVE-2022-50182

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 arbitrary W image width and H image height dimensions. Align upwards buffer size for both encoder and decoder. and leave the picture...

CVE-2022-50182

CVE-2022-50182 concerns a Linux kernel issue in the media: imx-jpeg driver. The flaw involved aligning upwards the buffer size for both encoder and decoder, allowing arbitrary image dimensions (WxH) while leaving the picture resolution unchanged. The documented impact indicates the decoder risk o...

CVE-2022-50182 media: imx-jpeg: Align upwards buffer size

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 arbitrary W image width and H image height dimensions. Align upwards buffer size for both encoder and decoder. and leave the picture...

CVE-2022-50182

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 arbitrary W image width and H image height dimensions. Align upwards buffer size for both encoder and decoder. and leave the picture...

CVE-2022-50182 media: imx-jpeg: Align upwards buffer size

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 arbitrary W image width and H image height dimensions. Align upwards buffer size for both encoder and decoder. and leave the picture...

KGMark: a Diffusion Watermark for Knowledge Graphs

Knowledge graphs KGs are ubiquitous in numerous real-world applications, and watermarking facilitates protecting intellectual property and preventing potential harm from AI-generated content. Existing watermarking methods mainly focus on static plain text or image data, while they can hardly be...

Astra Linux – Vulnerability in Linux 6.12

In the Linux kernel, the following vulnerability has been resolved: book3s64/radix : Align section vmemmap start address to PAGESIZE A vmemmap altmap is a device-provided region used to provide backing storage for struct pages. For each namespace, the altmap should belong to that same namespace. ...

Astra Linux – Vulnerability in Linux 6.12

In the Linux kernel, the following vulnerability has been resolved: bpf: Fixed a soft lockup issue in arenamapfree on 64k page kernels. In an aarch64 kernel with CONFIGPAGESIZE64KB=y, the arenahtab test causes a segmentation fault and a soft lockup. This same issue is not observed when using 4k...

Astra Linux - Vulnerability in linux-6.12

In the Linux kernel, the following vulnerability has been resolved: bpf: Fix kmemleak warning for percpu hashmap Vlad Poenaru reported the following kmemleak issue: unreferenced object 0x606fd7c44ac8 size 32: backtrace crc 0: pcpuallocnoprof+0x730/0xeb0 bpfmapallocpercpu+0x69/0xc0...

SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge

Large language models LLMs exhibit advancing capabilities in complex tasks, such as reasoning and graduate-level question answering, yet their resilience against misuse, particularly involving scientifically sophisticated risks, remains underexplored. Existing safety benchmarks typically focus...

CLSA-2025-1749562017 kernel: Fix of 24 CVEs

vsock: Keep the binding until socket destruction CVE-2025-21756 - mt76: fix use-after-free by removing a non-RCU wcid pointer CVE-2022-49328 - bpf, testrun: Fix alignment problem in bpfprogtestrunskb CVE-2022-49840 - ASoC: core: Fix use-after-free in sndsocexit CVE-2022-49842 - net: sched: Fix...

CLSA-2025-1749548218 Fix of 6 CVEs

CVE-url: https://ubuntu.com/security/CVE-2024-57896 - btrfs: flush delalloc workers queue before stopping cleaner kthread during unmount CVE-url: https://ubuntu.com/security/CVE-2024-56551 - drm/amdgpu: fix usage slab after free CVE-url: https://ubuntu.com/security/CVE-2021-47211 - ALSA: usb-audi...

DAVSP: Safety Alignment for Large Vision-Language Models Via Deep Aligned Visual Safety Prompt

Large Vision-Language Models LVLMs have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectivel...

Evaluation Empirique De La Sécurisation Et De L'Alignement De ChatGPT Et Gemini: Analyse Comparative Des Vulnérabilités Par Expérimentations De Jailbreaks

Large Language models LLMs are transforming digital usage, particularly in text generation, image creation, information retrieval and code development. ChatGPT, launched by OpenAI in November 2022, quickly became a reference, prompting the emergence of competitors such as Google's Gemini. However...

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment

Safely aligning large language models LLMs often demands extensive human-labeled preference data, a process that's both costly and time-consuming. While synthetic data offers a promising alternative, current methods frequently rely on complex iterative prompting or auxiliary models. To address...

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation RAG systems enhance Large Language Models LLMs by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on...

Why LLM Safety Guardrails Collapse after Fine-Tuning: a Similarity Analysis between Alignment and Fine-Tuning Datasets

Recent advancements in large language models LLMs have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies primarily focus on reactively addressing jailbreak incidents after safety guardrail...