Aggregator
Is OpenClaw an entry point for attackers?
CVE-2026-23138 | Linux Kernel up to 6.18.5 tracing recursion (Nessus ID 299078)
CVE-2026-23133 | Linux Kernel up to 6.18.7 wifi dma_free_coherent allocation of resources
CVE-2026-23163 | Linux Kernel up to 6.6.122/6.12.68/6.18.8 amdgpu vega10_ih_sw_init ring[] null pointer dereference
CVE-2026-23162 | Linux Kernel up to 6.18.8 nvm drm/xe/ auxiliary_device_init double free
CVE-2026-23135 | Linux Kernel up to 6.6.121/6.12.67/6.18.7 wifi dma_free_coherent allocation of resources
CVE-2026-23157 | Linux Kernel up to 6.18.8 btrfs io_schedule_timeout deadlock (Nessus ID 299067)
CVE-2026-23165 | Linux Kernel up to 6.18.8 sfc net_device deadlock
CVE-2026-23160 | Linux Kernel up to 6.6.122/6.12.68/6.18.8 octeon_ep octep_device_setup memory leak
CVE-2026-23158 | Linux Kernel up to 6.12.68/6.18.8 gpio mutex_unlock use after free
CVE-2026-23155 | Linux Kernel up to 6.6.122/6.12.68/6.18.8 gs_usb_receive_bulk_callback information exposure
Ваши карты «биты»: хакеры устроили в интернете глобальную инвентаризацию GeoServer
One threat actor responsible for 83% of recent Ivanti RCE attacks
NDSS 2025 – Black-Box Membership Inference Attacks Against Fine-Tuned Diffusion Models
Session 12C: Membership Inference
Authors, Creators & Presenters: Yan Pang (University of Virginia), Tianhao Wang (University of Virginia)
PAPER
Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
With the rapid advancement of diffusion-based image-generative models, the quality of generated images has become increasingly photorealistic. Moreover, with the release of high-quality pre-trained image-generative models, a growing number of users are downloading these pre-trained models to fine-tune them with downstream datasets for various image-generation tasks. However, employing such powerful pre-trained models in downstream tasks presents significant privacy leakage risks. In this paper, we propose the first scores-based membership inference attack framework tailored for recent diffusion models, and in the more stringent black-box access setting. Considering four distinct attack scenarios and three types of attacks, this framework is capable of targeting any popular conditional generator model, achieving high precision, evidenced by an impressive AUC of 0.95.
ABOUT NDSS
The Network and Distributed System Security Symposium (NDSS) fosters information exchange among researchers and practitioners of network and distributed system security. The target audience includes those interested in practical aspects of network and distributed system security, with a focus on actual system design and implementation. A major goal is to encourage and enable the Internet community to apply, deploy, and advance the state of available security technologies.
Our thanks to the Network and Distributed System Security (NDSS) Symposium for publishing their Creators, Authors and Presenter’s superb NDSS Symposium 2025 Conference content on the Organizations' YouTube Channel.
The post NDSS 2025 – Black-Box Membership Inference Attacks Against Fine-Tuned Diffusion Models appeared first on Security Boulevard.
SecWiki News 2026-02-14 Review
评估与增强大语言模型解决夺旗赛挑战的能力 by ourren
PentestAgent:将LLM代理融入自动化渗透测试 by ourren
2025年全球身份认证攻击风险研究报告 by ourren
JoySafeter:AI驱动安全(AISecOps)新范式 by ourren
更多最新文章,请访问SecWiki