Agent Safety Alignment Via Reinforcement Learning

The emergence of autonomous Large Language Model LLM agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to both user-initiated threats e.g., adversarial prompts and...

TuneShield: Mitigating Toxicity in Conversational AI While Fine-Tuning on Untrusted Data

Recent advances in foundation models, such as LLMs, have revolutionized conversational AI. Chatbots are increasingly being developed by customizing LLMs on specific conversational datasets. However, mitigating toxicity during this customization, especially when dealing with untrusted training dat...

Phantom Subgroup Poisoning: Stealth Attacks on Federated Recommender Systems

Federated recommender systems FedRec have emerged as a promising solution for delivering personalized recommendations while safeguarding user privacy. However, recent studies have demonstrated their vulnerability to poisoning attacks. Existing attacks typically target the entire user group, which...

Linux kernel 安全漏洞

Linux kernel is the kernel used by Linux, the open source operating system of the Linux Foundation in the United States. A security vulnerability exists in Linux kernel that stems from a kernel bug triggered when encrypted inode file sizes are not aligned...

SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning

Federated Learning FL has emerged as a leading paradigm for privacy-preserving distributed machine learning, yet the distributed nature of FL introduces unique security challenges, notably the threat of backdoor attacks. Existing backdoor strategies predominantly rely on end-to-end label...

Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks

The widespread deployment of large language models LLMs has raised critical concerns over their vulnerability to jailbreak attacks, i.e., adversarial prompts that bypass alignment mechanisms and elicit harmful or policy-violating outputs. While proprietary models like GPT-4 have undergone extensi...

O2Former:Direction-Aware and Multi-Scale Query Enhancement for SAR Ship Instance Segmentation

Instance segmentation of ships in synthetic aperture radar SAR imagery is critical for applications such as maritime monitoring, environmental analysis, and national security. SAR ship images present challenges including scale variation, object density, and fuzzy target boundary, which are often...

Doppelgänger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack

Since the advent of large language models, prompt engineering now enables the rapid, low-effort creation of diverse autonomous agents that are already in widespread use. Yet this convenience raises urgent concerns about the safety, robustness, and behavioral consistency of the underlying prompts,...

SUSE 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...

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 the start address of the vmemmap section with PAGESIZE. The vmemmap altmap is a device-provided region used to provide backing storage for struct pages. For each namespace, the altmap should belong to the sa...

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...