ZeroHour
DashboardNewsCVEsExploitsIncidentsAIBriefAnalyticsEntitiesWatchlistIOCsAsk the feedSourcesFeeds & APIKiosk mode

Search: “llm serving”

268 items

Searchkeywordsmart Sortlatesthotimportancerelevance
DomainAllCyberAIWindow24h3d7d30dAllIn the wildImportant onlyShow duplicates
CategoryAllMalware 46Vulnerability 32AI safety & security 29Threat actor 28Exploit / PoC 21Policy & legal 21Ransomware 19Model release 13AI research 11Phishing & fraud 11Research 9AI industry 8AI tools & infra 7Data breach 6
SeverityAllcritical 77high 48medium 61low 31info 51

HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

HoneyRoute detects malicious LLM serving requests and diverts them to a honeypot model, reaching F1 0.911 with 38 ms median added latency.

HoneyRoute is an inference-serving layer pairing a streaming router (a frozen 0.8B embedding backbone with per-domain MLP heads) with a dual-implementation honeypot and an analysis loop that converts trapped interactions into attacker fingerprints for router retraining. On a production trace plus a seven-domain attack corpus it matches 96% of a two-tier guard-LLM cascade's F1 at 1/385th of its latency with 0% evasion under 13 adversarial transformations. Diverting malicious traffic cuts production token consumption under GCG-suffix flooding by 97.8%, and loop training raises detection F1 to 0.933.

arXiv cs.CR · 8d agoAI safety & security

The Self-Expanding Stolen Inference Supply Chain: An AI Agent Harvesting and Re-Serving LLM Access, (Fri, Sep 11th)

An autonomous coding agent harvested LLM API access from poorly secured gateways and aggregated stolen inference capacity behind a self-hosted gateway

A SANS researcher observed a semi-autonomous coding agent finding weakly secured LLM resale gateways via FOFA queries, creating trial accounts with temporary emails and CAPTCHA solving, and exploiting weak authorization such as client-supplied group_id fields. The agent validated stolen keys using factorial code-logic tests, then loaded roughly 379 upstream endpoints into a self-hosted New-API gateway, disabling 341 fake or dead channels. Five model names including claude-opus-5 and gpt-5.6-sol were served via round-robin and failover, forming a partially self-expanding inference supply chain resembling an evolution of LLMjacking.

SANS Internet Storm Center · 5d agoThreat actor in the wild

JustFit: 200K-Token LLM Serving on a 24 GiB Laptop with Just-in-Time State Management

JustFit MLX runtime serves 200K-token contexts for Qwen3.8-27B on a 24 GiB MacBook via just-in-time state management.

JustFit is an MLX-based inference runtime combining KVExec for compressed KV execution, PhaseSwap for component residency, and StateTrans for state-preserving serving transitions, independent of weight quantization. On a 24 GiB M4 Pro MacBook running Qwen3.8-27B MXFP4, it completed 196,608 input and 16,384 output tokens, raising single-request context from the mlx-vlm baseline's 30,720 positions to 212,992 (6.93x). Performance tests show 19.11 tokens/s on a 32K-input probe with a 16,374 MiB median peak footprint, and the runtime answered 29 of 30 AIME 2026 problems correctly.

arXiv cs.AI / cs.LG / cs.CL · 1d agoAI research

Speculative Decoding in vLLM on AMD GPUs

vLLM benchmarks speculative decoding on AMD Instinct MI300X and MI355X GPUs across five drafting methods including EAGLE-3 and native MTP.

The vLLM project documents draft-and-verify speculative decoding support for AMD GPUs via ROCm, comparing native MTP, Gemma 4 MTP, EAGLE-3, DFlash, and DSpark drafting approaches. Output-token throughput effects varied with drafting method, proposal length, model family, draft checkpoint, workload, and acceptance behavior. The post also covers how to enable each method plus practical tuning and observability considerations.

Hacker News · AI · 9d agoAI tools & infraHN 141↑ · 52 comments1

SpecGuard: Inference-Time Backdoor Detection For Free

SpecGuard detects backdoored LLM behavior at inference time using speculative decoding acceptance rates, adding no extra model computation.

Researchers propose SpecGuard, an inference-time backdoor detector that repurposes draft-token acceptance rates from speculative decoding as a detection signal at zero added model-computation cost. When a trigger shifts the target model toward attacker-controlled behavior, the clean draft model's acceptance rate changes, exposing the backdoor; the paper formalizes when this signal appears and shows suppressing it weakens the backdoor. Experiments across diverse backdoor types and model families show reliable detection, including stealthy cases invisible to input-level filters. Speculative decoding is positioned as a free, always-on monitor for frequently updated deployed models.

arXiv cs.CR · 6d agoAI safety & security 2 sources2

DeepSeek AI Released DeepSeek-V4.1-Flash with 1M Context, FP4 KV Cache, and Cross-Layer Attention Reuse

DeepSeek released open-weight V4.1-Flash, a 552B MoE model with 1M context and FP4 KV cache, beating Opus-5 and GPT-5.6 Sol on agent benchmarks.

DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with a 552B-parameter backbone plus 196B Engram parameters, activating 8B parameters at prefill and 16B at decode, with a 1M-token context window. It introduces a causal encoder-decoder design, Compressed Sparse Attention 2, and FP4 (E2M1) KV cache quantization, cutting global KV cache to 890 bytes per token, about 1/4 of V4-Flash and 437x smaller than V1. Pre-training covered 45T multimodal tokens; the MIT-licensed weights ship on Hugging Face with vLLM and SGLang support. It scores 90.6 on Terminal-Bench 2.1 and 74.2 on DeepSWE v1.1, ahead of Opus-5 and GPT-5.6 Sol.

MarkTechPostupdated · 4d agofirst · 6d agoModel release 4 sources1

Perplexity Details Its GPU Embedding Stack: How Ivy, Tulip and ROSE Serve pplx-embed

Perplexity details its GPU embedding serving stack (Ivy, Tulip, ROSE), which reuses LLM prefill/decode kernels, CUDA graphs, and LazyTensors to cut launch overhead.

Perplexity engineers published a deep dive on the serving infrastructure behind pplx-embed, used across Perplexity Search and its API platform. The stack comprises Ivy (Rust HTTP gateway), Tulip (gRPC scheduling and batching), and ROSE (Runtime-Optimized Serving Engine), which reuses LLM prefill and decode kernels rather than running a separate embedding engine. Optimizations include whole-model CUDA graphs with lazy capture and a LazyTensor abstraction that overlaps CPU batch preparation with in-flight GPU work. Benchmarks are reported against vLLM v0.22.0 in BF16, with FlashAttention 4 generally fastest but FlashInfer 3 winning on Qwen-based models at very long sequence lengths.

MarkTechPost · 10d agoAI tools & infra1

Agentic Visual Generation: From Generative Models to Agentic Control

Researchers propose an L0-L4 control taxonomy for agentic visual generation, classifying controllers from fixed conditioning to experience-adaptive decision-making.

This paper proposes a taxonomy for agentic visual generation organized by what the controller can directly control in the generation process, rather than by planning depth, tool count, or model size. Levels range from L1 Conditioning Control through L2 Execution Control, L3 Outcome-Adaptive Control, and L4 Experience-Adaptive Control, with L0 Fixed Support denoting systems without a deployed decision-making controller. The framework is applied across image, video, editing, 3D, world, slide, and user-interface generation to map how controller capabilities and mechanisms have evolved across the field.

Hugging Face daily papers · 11d agoAI research

The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RAN

OCUDU open runtime lets third-party signed AI-RAN dApps run inside production 5G distributed units under three timing contracts, released as BSD-3 preview.

The OCUDU dApp platform provides an open runtime and E3 interface for executing signed AI-RAN applications inside a production 3GPP NR distributed unit, where prior dApp frameworks could only observe export streams. Modules run under three typed timing contracts: GPU receive-chain residency (Class A), the scheduler's 100 microsecond deadline (Class B), or non-blocking observer (Class C). On a GB10 gNB, dApps including an out-of-tree neural equalizer ran on a live cell without fallback. Platform, SDK, and a zero-hardware quickstart are public under BSD-3-Clause-Clear as a preview of the OCUDU AI-RAN Working Group 2.

arXiv cs.AI / cs.LG / cs.CL · 9d agoAI tools & infra1

When LLM Decompilers Recompile More and Preserve Less

Researchers show LLM decompiler outputs can recompile yet diverge behaviorally, proposing the Decompile-Diverge fuzzing oracle to catch hidden changes.

The paper demonstrates that LLM-based decompilers can produce code that recompiles and passes all shipped tests yet diverges on other legitimate inputs—4.9% overall and up to 13% for one system—and can make disclosed vulnerabilities vanish without a visible crash. Across 300 real GitHub functions and 287 CVE-grounded functions, a refinement LLM lifted Ghidra's build rate from 75% to 90% while Matched rate fell from 74% to 62%, with up to one tenth of vulnerabilities showing Crash Absence. Decompile-Diverge detects these gaps by synthesizing drivers, growing fuzzing corpora from the reference, and rerunning decompiled code on identical inputs.

arXiv cs.CR · 12d agoResearch

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

Mind2Dialogue simulates users' mental states to create privileged supervision, boosting personalization metrics of Qwen, Llama, and OLMo assistants by up to 40.9 points.

The paper proposes a psychology-guided simulator that preserves personal characteristics while evolving shared mental states to generate coherent conversations, with an Oracle assistant grounded in those states. Privileged distillation then trains models on Oracle responses so deployed assistants help users without direct mental-state access. Training on the full corpus improves every personalization metric over Qwen, Llama, and OLMo instruction-tuned baselines, including 26.6 to 40.9 percentage point gains in preference-following generation and improved belief/action reasoning.

arXiv cs.AI / cs.LG / cs.CL · 2d agoAI research 2 sources1

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

Mind2Dialogue simulates users' mental states to generate privileged supervision, boosting personalization and preference-following in Qwen, Llama, and OLMo assistants.

The Mind2Dialogue framework uses a psychology-guided simulator that preserves personal characteristics while updating user mental states through interaction, driving coherent conversations and an Oracle assistant's responses. Privileged distillation trains models on the Oracle's well-informed responses so they can assist users without direct access to mental states at deployment. Training on the full corpus improves every reported personalization metric over Qwen, Llama, and OLMo instruction-tuned baselines, including 26.6 to 40.9 percentage point gains in preference-following generation.

Hugging Face daily papersupdated · 2d agofirst · 3d agoAI research 2 sources

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

Researchers propose provenance-guided selective replay letting LLM agents forget revoked information without restarts, matching full reset behavior.

The paper formalizes execution-state unlearning for stateful LLM agents, requiring that agents behave as if a revoked memory record was never observed across transcripts, compressed memory, tool plans, and KV caches. It proves exact unlearning requires at least T-τ+1 recomputed transitions and that Provenance-Guided Selective Replay attains this bound via a provenance graph, KV cache cropping, and sanitized replay. In audits across three agent suites, nine baselines, and three model families, memory deletion left leakage unchanged, instruction-based forgetting collapsed under elicitation (Leak@probes = 1.00), and selective replay matched full resets at up to 9x fewer recomputed tokens.

arXiv cs.CR · 12d agoAI safety & security1

Wazuh and AI For Enhanced SOC Workflows

Wazuh details AI-powered SOC workflows via its AI Analyst, self-hosted Llama 3 via Ollama, and Claude 3.5 Haiku integrations.

Wazuh outlines how AI can augment SOC analysts handling high alert volumes. The Wazuh AI Analyst on Wazuh Cloud uses Amazon Bedrock and Anthropic Claude to generate scheduled security posture reports. Self-hosted options include Llama 3 with Ollama, FAISS, and LangChain for privacy-sensitive threat hunting, plus an OpenSearch Assistant integration with Claude 3.5 Haiku. This is a vendor-contributed piece describing product capabilities rather than an incident or vulnerability.

The Hacker News · 26d agoTools