60
30
60
30
30
30
35
Distance generalization in transformers: why bother with positional encoding?
arXiv study uses synthetic delay-copy tasks to show how RoPE, ALiBi, NoPE and training data diversity affect transformers' distance generalization.
The paper studies distance generalization in transformers: extrapolating when inter-token distances change between training and inference while context length stays fixed. Using two synthetic delay-copy tasks with finite source-recall distances, the authors test models on unseen delays. They investigate whether positional encodings such as RoPE and ALiBi outperform no positional encoding (NoPE), how the diversity of training distances affects performance, and when distance transfer learning is positive or negative.
30
Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates
Researchers propose FedIoC, a federated learning framework detecting cross-organization attack campaigns from threat-indicator structure in gradient updates without sharing IoCs.
The paper introduces FedIoC, a modular federated learning framework in which clients encode locally matched indicators of compromise into gradient updates using a supervised contrastive loss over IoC-matched flows. The server clusters client updates by cosine similarity to recover global attack-campaign patterns without any direct IoC transmission across organizational or national boundaries. Evaluations on two public threat-detection benchmarks, distributed across clients holding only fragments of each campaign and disjoint indicator sets, show the server recovers cross-organizational campaign cohorts from gradient geometry alone. The authors identify non-IID gradient structure as the main driver of recovery and define open problems for encoder design.
32
NeoMME: an efficient Multimodal-native and Multilingual Encoder
H Company released NeoMME, an efficient multimodal-native and multilingual encoder, via a post on the Hugging Face blog.
H Company published a Hugging Face blog post introducing NeoMME, described as an efficient multimodal-native and multilingual encoder. The article body was unavailable in the feed, so architecture, benchmarks, and licensing details could not be verified. The post suggests a new encoder release relevant to multilingual multimodal model development.
32
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp — new model trending #10 on Hugging Face
DeepSeek released DeepSeek-V4-Flash-Vision-Exp, its first experimental multimodal model, with large multimodal agent benchmark gains over V4-Flash-0731.
DeepSeek AI published DeepSeek-V4-Flash-Vision-Exp, an experimental multimodal model built on the DeepSeek-V4-Flash architecture with added visual modules and continued training. It scores 83.9 on Terminal Bench 2.1 and 36.5 on ApexBench Pass@1 versus 26.2 for DeepSeek-V4-Flash-0731, while remaining comparable to Opus-4.8 on several benchmarks. The MIT-licensed repository ships a tokenizer, OpenAI-style and TXT prompt encoding, and a minimal PyTorch inference implementation, with vLLM and SGLang deployment recipes.
68
Content-Encoding WAF Evasion
FortiWeb WAF policies can be bypassed by unauthenticated attackers using crafted Content-Encoding requests (CVSS 4.8).
Fortinet disclosed an incomplete list of disallowed inputs (CWE-184) in FortiWeb's WAF, tracked as FG-IR-26-157. An unauthenticated attacker can bypass WAF policies using specifically crafted requests with crafted Content-Encoding values. The issue carries a CVSSv3 score of 4.8 and was revised on 2026-08-12. The advisory does not report active exploitation.
22
30
60
42
30
55
60
45
30
30
57
60
30
30
30
42
60
45
30
Google’s New Search Redirects Make It Harder to Check Where Links Lead Before Clicking
Malwarebytes reports Google's new encoded google.com/goto?url= redirects break hover-preview link checking, weakening a common phishing defense.
Google now routes some search results through opaque google.com/goto?url= redirects using custom encoding, so browser link previews no longer reveal the true destination, only the claimed label above the result. Malwarebytes found the final destination is visible only in the redirect response's Location header, complicating hover-based safety checks as well as scraping, archiving, and audit tools. The change arrives amid malvertising, search-result poisoning, and fake installer campaigns like the recent Node.js infostealer lure. Google says it deploys measures against evolving abuse but did not explain the change.
30
Viggle/Viggle-Animate — new model trending #28 on Hugging Face
Viggle released Viggle-Animate, a 33.1B MiniMax-H3 finetune replacing video characters from one repainted frame, rendering 124 frames in 26 seconds on one GPU.
Viggle-Animate replaces the character in a video using only a driving video and one of its own repainted frames, with no pose estimator, segmentation mask, face tracker, or text encoder. It is a 33.1B full finetune of MiniMax-H3's ref2va transformer, jointly distilled with DMD across two teachers split by noise level, so rendering takes three forward passes per clip. On a B200 GPU it renders 124 frames in 26 seconds, 6.1x faster per clip than Wan2.2-Animate-14B in matched comparisons. The method assumes no person-specific representation, so it generalizes beyond humans; a demo, research write-up, and ComfyUI nodes are available.
40
Learning Sparse Decision Trees via Transformer Variational Auto-Encoders
TREVIS uses a Tree Transformer VAE latent space to learn decision trees matching near-optimal predictive performance while improving structural sparsity.
TREVIS learns decision trees optimized for complex objectives by exploring the latent space of a Tree Transformer Variational Auto-Encoder (TTVAE). Mapping trees to continuous latent representations replaces the discrete search space with a continuous one, enabling gradient-based optimization through a differentiable surrogate model. Experiments show TREVIS matches the predictive performance of near-optimal algorithms while improving structural sparsity, targeting high-stakes contexts needing transparent decision logic.
18
Threat Brief: OWASSRF Vulnerability Exploitation
Unit 42 details active exploitation of Exchange SSRF flaws CVE-2022-41080/CVE-2022-41082 via the OWASSRF method, deploying the SilverArrow PowerShell backdoor.
Unit 42 documents OWASSRF, an exploit chain combining CVE-2022-41080 and CVE-2022-41082 to achieve remote code execution on Microsoft Exchange via Outlook Web Access, bypassing Microsoft's ProxyNotShell mitigations. Active exploitation was observed in late November and early December 2022, affecting at least eight organizations. Attackers authenticated to Exchange, then executed a PowerShell backdoor tracked as SilverArrow to create admin accounts, install AnyDesk, tunnel RDP via PuTTY Link, and dump LSASS memory for credential theft. Exploitation is isolated rather than mass-scale because authentication is required.
55
30
42
30
30
45
30