Search: “SAP BW/4HANA”

29 stories

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Industry 2 Vulnerability 2 Exploit / PoC 1

SeverityAll critical 2 high 1 medium 0 low 2 info 0

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

SAP Patches Critical Extended Passport Processing Vulnerability

SAP patches CVSS 10.0 flaw CVE-2026-44756 (OVERPASS) enabling unauthenticated RCE in S/4HANA and NetWeaver, plus three other criticals; no in-the-wild exploitation reported.

CVE-2026-44756 is a CVSS 10.0 memory corruption flaw in Extended Passport (EPP) deserialization, triggered when a user session opens across web, SAP GUI, and RFC vectors. Exploitation yields command execution as the SAP OS account, database credential and password hash recovery, session reading, and data or binary modification; affected products include S/4HANA, ERP/ECC, NetWeaver, Web Dispatcher, and BW/4HANA. Three other criticals were patched: CVE-2026-58240 (S4GET, missing authentication affecting all S/4HANA 2025 and earlier releases), CVE-2026-76969 (CAP credential disclosure), and CVE-2026-66768 (NetWeaver access control). Onapsis and SAP report no indicators of in-the-wild exploitation.

SecurityWeekSep 8, 14:55 UTC · 8d agoVulnerability 2 sources CVE-2026-44756 CVE-2026-58240 CVE-2026-76969+1 CVEs

2026-011: Critical Vulnerabilities in SAP Kernel and NetWeaver Message Server

SAP patched two critical flaws, OVERPASS (CVE-2026-44756, CVSS 10.0) and S4GET (CVE-2026-58240), allowing unauthenticated attackers to execute OS commands on SAP hosts.

On SAP's September 2026 Security Patch Day, SAP released Security Notes 3747649 and 3759472 fixing two critical unauthenticated remote vulnerabilities found by Onapsis. CVE-2026-44756 ('OVERPASS', CVSS 10.0) is a memory corruption flaw in Extended Passport (EPP) deserialisation in the SAP Kernel; CVE-2026-58240 ('S4GET', CVSS 9.8) is a missing authentication check in the NetWeaver Message Server that lets attackers register as trusted cluster nodes. Successful exploitation of either can yield OS command execution as the SAP service account, leading to full system and business data compromise, and CERT-EU urges immediate patching. No in-the-wild exploitation is reported.

CERT-EU AdvisoriesSep 9, 00:00 UTC · 8d agoVulnerability CVE-2026-44756 CVE-2026-58240

TokenRhythm/NeoHorse-1-4B — new model trending #30 on Hugging Face

TokenRhythm releases NeoHorse-1-4B, an Apache-2.0 agentic fine-tune of Qwen3.5-4B claiming +5.93 benchmark macro-average gain.

NeoHorse-1-4B is a roughly 4B-parameter text-only causal language model post-trained by TokenRhythm from Qwen/Qwen3.5-4B for agent harnesses, tool use, coding, and instruction following. It applies routing-guided curriculum SFT and routing-guided on-policy distillation over execution trajectories as an early prototype toward recursive self-improvement (RSI). The release reports a 64.87 macro average across ten benchmarks versus 58.94 for Qwen3.5-4B (+5.93) and is distributed under Apache-2.0, trending #30 on Hugging Face.

Hugging Face trending modelsSep 5, 08:21 UTC · 11d agoModel release1

Facilitating AI integration with simplicity at scale

Jabil's SAP IT director says simplifying integration across 100+ sites in 30+ countries with SAP Integration Suite created the data backbone for AI.

In an MIT Technology Review Business Lab podcast produced in partnership with SAP, Jabil SAP IT director Harish Manohar described consolidating fragmented tools across more than 100 sites in over 30 countries using SAP Integration Suite. The manufacturer, with 140,000-plus employees and more than 400 top-brand customers, says a standardized data backbone enables real-time supply chain visibility and is a prerequisite for scaling predictive, AI-driven planning and forecasting. The company frames simplification-first modernization as a competitive advantage tied to measurable business value and operational resilience.

MIT Technology Review · AISep 2, 14:00 UTC · 14d agoAI industry1

Identifying a BOLA Vulnerability in Harbor, a Cloud

Unit 42 found a BOLA flaw, CVE-2024-22278 (CVSS 6.4), letting Maintainers improperly alter Harbor project metadata; fixed in versions 2.9.5, 2.10.3, and 2.11.0.

Unit 42 researchers identified a broken object-level authorization flaw, CVE-2024-22278, in Harbor, a CNCF-graduated cloud-native container registry with 1.8 million downloads. The flaw (CVSS 6.4) lets users with the Maintainer role create, update, and delete project metadata, actions reserved for ProjectAdmin, risking data exposure, integrity compromise, and circumvention of vulnerability scanning. Harbor patched the issue in versions 2.9.5, 2.10.3, and 2.11.0. The finding came from Unit 42's automated BOLA detection tool built on generative AI.

Palo Alto Unit 42Aug 17, 12:35 UTC · Aug 17, 2026Vulnerability CVE-2024-22278

SAP security advisory – September 2026 monthly rollup (AV26-894)

Canada's Cyber Centre relayed SAP's September 2026 Patch Day rollup covering vulnerabilities across NetWeaver, kernel components, CAP, and Integration Suite.

The Canadian Centre for Cyber Security published advisory AV26-894 noting that as of September 8, 2026, SAP is affected by vulnerabilities in multiple products, including SAP Extended Passport, NetWeaver Message Server, SAP Cloud Application Programming Model, SAP GUI for Java, Integration Suite Cloud Integration, NetWeaver Business Client, and NetWeaver AS for ABAP. The advisory corresponds to SAP Security Patch Day September 2026 and lists many affected kernel and web dispatcher versions. Administrators are urged to review the SAP advisory and apply updates as available.

Canadian Centre for Cyber SecuritySep 8, 18:03 UTC · 8d agoAdvisory

SAP Commerce Cloud CVE-2026

Attackers actively exploit unauthenticated RCE CVE-2026-58231 (CVSS 10.0) in SAP Commerce Cloud days after patch release.

CVE-2026-58231, a maximum-severity flaw in SAP Commerce Cloud (CVSS 10.0), allows unauthenticated attackers to abuse a default authentication client and bypass insufficient validation, achieving arbitrary code execution and compromise of internal components. Defused Cyber researchers observed exploitation attempts against honeypots only three days after SAP released the patch. The flaw had no public PoC and was not previously known to be exploited. The attackers are unknown, though past critical SAP flaws have been exploited by China-linked groups UNC5221 and UNC5174 and ransomware gangs.

Security AffairsAug 15, 17:14 UTC · Aug 15, 2026Exploit / PoC in the wildCVE-2026-58231

SAP Patches CVSS 10.0 Kernel Flaw Enabling Unauthenticated Remote Code Execution

SAP patched CVE-2026-44756 (CVSS 10.0), an unauthenticated kernel memory corruption allowing OS command execution, plus three other critical flaws.

SAP's September security updates include CVE-2026-44756 (OVERPASS, CVSS 10.0), a missing boundary validation during deserialization of Extended Passport (EPP) data in the SAP kernel, enabling unauthenticated attackers to run arbitrary OS commands with SAP administrative privileges. Also patched: CVE-2026-58240 (S4GET, CVSS 9.8), a missing authentication check in SAP NetWeaver Message Server yielding RCE as <sid>adm; CVE-2026-76969 (9.4), credential disclosure in SAP Cloud Application Programming Model multi-tenant apps; and CVE-2026-66768 (9.0), improper access control in SAP NetWeaver SAP GUI for Java. Onapsis, which discovered the flaws, says none have been exploited to date and recommends prioritizing internet-facing SAP systems.

The Hacker NewsSep 9, 06:25 UTC · 7d agoVulnerability CVE-2026-44756 CVE-2026-58240 CVE-2026-76969+1 CVEs

IFM/K2-Horizon-MoVA-36B-A4B — new model trending #15 on Hugging Face

IFM released K2-Horizon-MoVA-36B-A4B, an open-weights 36B-parameter MoE model with 4B active parameters and native 512K context.

IFM released the final checkpoint of K2-Horizon-MoVA-36B-A4B, a sparse Mixture-of-Experts model using Mixture-of-Values (MoVA) attention with 36B total and 4B active parameters. The model supports native 524,288-token context and reportedly outscores open-weight dense and MoE models up to 15x its size on agentic and reasoning benchmarks, while competing against closed frontier models. Intermediate checkpoints, training data, the training recipe, and training code are slated for public release.

Hugging Face trending modelsSep 1, 23:01 UTC · 15d agoModel release

Notes on gotchas while migrating 35kb preprompts from Opus to self-hosted Ollama

Opinion piece urges migrating 35KB preprompts from Anthropic/OpenAI to self-hosted Ollama, citing session privacy risks and safety filters blocking security research.

The author documents gotchas migrating 35KB preprompts from Claude Opus to self-hosted Ollama, motivated by fears that frontier providers train on user sessions, citing the OpenAI Navier-Stokes controversy. The piece argues inference providers cannot audit their own retention or training pipelines and that only self-hosted hardware offers verifiable privacy. It also criticizes frontier safety filters for refusing vulnerability research tasks and calls for models that support exploitability testing in CI/CD pipelines.

Hacker News · AISep 14, 13:59 UTC · 2d agoAI industry HN 41↑ · 13 comments1

GitHub Introduces Project HydraFusion: Runtime Multi-Model Orchestration That Builds a Workflow Per Coding Task in Copilot CLI

GitHub's Project HydraFusion research preview builds per-task multi-model workflows (Single, Cascade, Critique) in Copilot CLI, reporting +4.9 quality at 67% lower cost on TerminalBench 2.1.

Project HydraFusion is a research preview available on all GitHub Copilot plans inside Copilot CLI that treats model routing as workflow selection, choosing among Single, Cascade (draft plus quality gate), and Critique (cross-family reviewer) execution patterns per request. Against Claude Opus 5 baselines at medium reasoning, fixed HydraFusion policies cut estimated cost 67% while adding 4.9 quality points on TerminalBench 2.1, and cut cost 36% and 65% with slight quality dips on DeepSWE and CheckpointBench. Billing is per token at each underlying model's standard rate; there are no open weights or self-hosting options.

MarkTechPostSep 5, 19:40 UTC · 11d agoAI tools & infra1

SAP Patches Maximum Severity “Overpass” Flaw

Onapsis warns over 10,000 internet-facing SAP systems may be exposed to maximum-severity unauthenticated RCE flaw CVE-2026-44756 in SAP Extended Passport.

Onapsis Research Labs discovered CVE-2026-44756, a memory corruption flaw in SAP Extended Passport (EPP) processing caused by missing boundary validation during deserialization. The bug is reachable from the SAP GUI and RFC layers, is remotely exploitable without authentication by default, and could let attackers run arbitrary OS commands with SAP administrative privileges. No active exploitation was observed at publication. Onapsis also flagged critical S4GET bug CVE-2026-58240 (CVSS 9.8) in the S/4HANA Message Server, credential disclosure CVE-2026-76969 in SAP CAP, and improper access control CVE-2026-66768 in NetWeaver.

Infosecurity MagazineSep 9, 08:15 UTC · 7d agoVulnerability CVE-2026-44756 CVE-2026-58240 CVE-2026-76969+1 CVEs

CVE-2026-82428: Apache Storm Client: Cross-Tenant Dependency Jar Substitution via Predictable Blob Keys

Apache Storm stores shared dependency jars under predictable Maven-derived blob keys, allowing one tenant to substitute jars other tenants execute.

CVE-2026-82428 affects Apache Storm Client (org.apache.storm:storm-client) versions 3.0.0 before 3.1.0, rated important. Dependency artifacts uploaded with storm jar --artifacts were stored under blob keys derived only from the Maven coordinate, making keys identical and predictable for every cluster user. When a blob already existed, the uploader suppressed the collision, enabling a tenant to substitute dependency jars later executed by other tenants in cross-tenant attacks. Fixed in version 3.1.0.

oss-securitySep 13, 14:23 UTC · 3d agoVulnerability CVE-2026-82428

SAP Security Updates September 2026 – Critical Flaws Patched in SAP NetWeaver, Cloud and Extended Passport

SAP's September 2026 Patch Day fixes 19 notes including CVE-2026-44756 (CVSS 10.0), unauthenticated memory corruption in SAP Extended Passport Processing kernels.

SAP shipped 19 new security notes plus one update across NetWeaver, S/4HANA, Integration Suite, Commerce Cloud, and Cloud Application Programming Model. Top issues include CVE-2026-44756 (CVSS 10.0 memory corruption in SAP Extended Passport Processing across many KERNEL and Web Dispatcher versions), CVE-2026-58240 (CVSS 9.8 missing authentication in NetWeaver Message Server), CVE-2026-76969 (CVSS 9.4 credential disclosure in CAP library sap/cds-mtxs), and CVE-2026-66768 (CVSS 9.0 access control flaw in SAP GUI for Java). No exploitation is reported; organizations running affected kernels are urged to patch urgently.

Cyber Security NewsSep 8, 11:19 UTC · 8d agoVulnerability CVE-2026-44756 CVE-2026-58240 CVE-2026-76969+17 CVEs

Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness

Systematic review of 66 studies finds LLMs for HVAC operations are mostly research-stage, with no ready-now deployment and only four pilot-level studies.

A critical review of 66 peer-reviewed studies from 2023 to March 2026 examines LLMs for HVAC operations in building energy systems. Only four studies reach pilot-level evidence, none reports sustained operational deployment, and 63 of 66 are research-only. Conventional ML, MPC, and RL remain dominant for high-frequency control and short-horizon forecasting, and the evidence supports LLMs primarily as semantic and workflow layers rather than autonomous controllers.

arXiv cs.AI / cs.LG / cs.CLSep 4, 16:08 UTC · 12d agoAI research

Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs

Attack shows unaligned orchestrators can launder capabilities from aligned frontier LLMs via benign subtask consultation, raising Gemma-4-31B CBRN rubric score from 62.3 to 83.1.

The paper introduces capability laundering, where a weaker unaligned model decomposes a harmful task into benign-looking subproblems, queries a stronger aligned model on each, and recombines answers locally, bypassing per-interaction safety evaluations. Evaluation used GPT-5.5, Claude Opus 4.8, and Grok-4.3 as consultants to four local orchestrators on CyBench, BountyBench, and CBRN tasks. On CyBench, Gemma-4-31B recovered 8/14 candidate tasks with GPT-5.5 and 7/9 with Opus, while Muse-Glimmer-30B recovered none. Across an eight-step hypothetical bioweapon attack chain, consultation raised Gemma-4-31B's mean rubric score from 62.3 to 83.1, exposing a gap in defenses that only refuse complete harmful tasks.

arXiv cs.CRSep 14, 11:10 UTC · 2d agoAI safety & security

CVE-2026-82441: Apache Storm Nimbus: Cross-Tenant Blob Deletion and Cluster Denial of Service via Unvalidated Topology Dependency Keys

Unvalidated topology dependency keys in Apache Storm Nimbus 3.0.0 enable cross-tenant blob deletion and cluster denial of service.

CVE-2026-82441 (severity: moderate) affects Apache Storm Nimbus (storm-server) versions 3.0.0 before 3.1.0. Topology submissions carry dependency_jars and dependency_artifacts blobstore key lists that Nimbus never validated on the submission path, yet acted on during cleanup of finished topologies. A malicious submitter could reference arbitrary blobstore keys, causing cross-tenant blob deletion and cluster-wide denial of service.

oss-securitySep 13, 14:42 UTC · 3d agoVulnerability CVE-2026-824411

Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization

ModerationBench shows foundation models can nearly triple Bluesky's moderation F1 (0.60 vs 0.22), with instruction- and example-driven guidance performing comparably.

Researchers built ModerationBench, a new benchmark of 4,000 manually annotated in-the-wild posts from Bluesky, to test whether foundation models can reliably operationalize content moderation policies. They systematically compare instruction-driven guidance (reasoning from policy precepts) with example-driven guidance (generalizing from precedents) for Vision-Language Models. Both paradigms achieve comparable peak effectiveness, and foundation models nearly triple the F1 of Bluesky's deployed moderation system on Random Posts (0.60 vs 0.22).

arXiv cs.AI / cs.LG / cs.CLSep 9, 16:30 UTC · 7d agoAI research1

How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing

Analysis of DeepSeek-V4-Flash shows four-stream mHC residual blocks use only about two streams effectively, with late-layer mixing providing little benefit.

The study examines the four-stream residual pathway of DeepSeek-V4-Flash, finding typical attention or FFN sites effectively use about two streams and that residual mixing is modest, occurring primarily in early layers. Replacing late mixers with identity increases C4 perplexity by only 1.9% while replacing early mixers raises it by 41%. Retaining the three largest routing weights per token increases perplexity by at most 2.7%, showing the model uses only part of the flexibility afforded by the four-stream design.

arXiv cs.AI / cs.LG / cs.CLSep 4, 16:02 UTC · 12d agoAI research

SAP Commerce Cloud Flaw Could Let Unauthenticated Attackers Execute Arbitrary Code

SAP patched a CVSS 10.0 unauthenticated RCE flaw (CVE-2026-58231) in Commerce Cloud's Data Hub Adapter, plus three critical flaws in NetWeaver and Manufacturing.

SAP's August 2026 updates fix CVE-2026-58231, a CVSS 10.0 flaw in Commerce Cloud's Data Hub Adapter where insufficient authorization checks and input validation let unauthenticated attackers execute arbitrary code. Onapsis urged customers to patch and redeploy, with an IP Filter Set on the vulnerable endpoint offered as a temporary workaround. The update also fixed CVE-2026-44772 (CVSS 9.9) and CVE-2026-44758 (CVSS 9.1), code injection flaws in Manufacturing Integration and Intelligence involving SSRF and SSTI, and CVE-2026-34265 (CVSS 9.8), an out-of-bounds write in NetWeaver ABAP's DIAG protocol parsing that can leak information or crash systems.

The Hacker NewsAug 12, 07:31 UTC · Aug 12, 2026Vulnerability CVE-2026-58231 CVE-2026-44772 CVE-2026-34265+1 CVEs

SAP September 2026 Security Update Fixes 4 Critical Vulnerabilities and 15 Other Flaws

SAP's September 2026 Patch Tuesday ships 19 security notes, including four criticals led by a CVSS 10.0 memory-corruption flaw in Extended Passport Processing.

SAP released 19 new Security Notes plus one update, fixing four critical vulnerabilities and 15 additional flaws. The most urgent is CVE-2026-44756 (CVSS 10.0), memory corruption in Extended Passport (EPP) Processing affecting many SAP Kernel and Web Dispatcher releases. Other criticals include CVE-2026-58240 (NetWeaver Message Server missing authentication, 9.8), CVE-2026-76969 (credential disclosure in CAP sap/cds-mtxs, 9.4), and CVE-2026-66768 (improper access control in SAP GUI for Java, 9.0). High-severity fixes cover XXE in Integration Suite Trading Partner Management, deserialization in NetWeaver Business Client, and memory corruption in NetWeaver AS for ABAP.

GBHackersSep 8, 10:24 UTC · 8d agoVulnerability CVE-2026-44756 CVE-2026-58240 CVE-2026-76969+8 CVEs1

[AINews] Claude Fable/Mythos 5.1: new SOTA model, 75% cache price cut but 70% more output tokens

Anthropic launched Claude Fable 5.1 and Mythos 5.1, claiming new SOTA benchmarks, with 75% cache-read price cut and 1M-token context.

Anthropic released Claude Fable 5.1 and Mythos 5.1 as flagship models for coding and knowledge work, with a 1M-token context window and pricing of $10/$50 per million input/output tokens and cache reads cut 75% to $0.25. Artificial Analysis Intelligence Index scored Fable 5.1 at 66 versus 63 for Claude Opus 5, with HLE at 59.1% and Terminal-Bench v2.1 at 91.4%, though per-task cost rose ~20% due to 1.7x output token usage. Community analysis suggested Fable and Mythos may share underlying weights with different safety/routing behavior, and release notes highlighted Enterprise Frontier Safeguards and zero-data-retention support.

Latent SpaceSep 2, 07:46 UTC · 14d agoModel release2

nvidia/Qwen3.8-Flash-Next-NVFP4 — new model trending #28 on Hugging Face

NVIDIA released an NVFP4 4-bit quantized build of Alibaba's Qwen3.8-Flash-Next, a 125B-parameter MoE vision-language model, via Model Optimizer.

The checkpoint quantizes Qwen3.8-Flash-Next — a hybrid-attention (Gated DeltaNet and Qwen Sparse Attention) Mixture-of-Experts model with 125B total and 6B activated parameters, plus 51B n-gram embeddings and 4B MTP — using NVIDIA Model Optimizer v0.46.0. NVFP4 benchmarks stay close to FP8: GPQA Diamond 91.5 vs 92.0, MMMU Pro 78.3 vs 77.1, Terminal-Bench 2.1 82.9 vs 83.3. It targets Blackwell B200/B300 GPUs, runs on vLLM, supports 262K context extendable to 1M tokens, and is licensed under the NVIDIA Open Model License with Qwen Community License 1.0.

Hugging Face trending modelsSep 2, 04:03 UTC · 15d agoModel release

XHToken/Spark-X2.5-4B-GGUF — new model trending #30 on Hugging Face

XHToken released GGUF weights of Spark-X2.5-4B, a compact model with 1M-token context and 200+ language support, under Apache 2.0.

The Hugging Face repository provides BF16 GGUF conversions of Spark-X2.5-4B, a compact general-purpose language model for conversation, writing, translation, reasoning, coding, tool use, and agentic workflows. The model uses a hybrid attention architecture, supports a native context length up to 1M tokens, and covers more than 200 languages. Local inference is supported through Ollama and LM Studio via an XHToken llama.cpp fork, with a --think=false flag to disable thinking mode for faster responses. Released under Apache License 2.0; it was trending #30 on Hugging Face at publication.

Hugging Face trending modelsAug 28, 11:26 UTC · 19d agoModel release

Synthesized builds Test Data Agent to validate AI agents with production-like data

Synthesized announced a Test Data Agent that provisions production-like data and system states to validate enterprise AI agents before deployment.

Synthesized unveiled its Test Data Agent, an agentic infrastructure capability that generates, masks, and subsets production-representative data for testing AI agents under realistic enterprise conditions. It integrates with agent development, evaluation, testing, and orchestration frameworks, with purpose-built support for complex SAP estates including finance, procurement, and supply-chain workflows and ECC-to-S/4HANA transformation programs. The product runs in on-premises, private-cloud, and hybrid environments and exposes REST APIs and CI/CD triggers for repeatable validation scenarios.

Help Net SecurityAug 18, 00:00 UTC · Aug 18, 2026AI tools & infra1

CVE-2026-82432: Apache Storm Nimbus: Blobstore Authorization Bypass via Rebalance Configuration Overrides

Apache Storm Nimbus blobstore authorization bypass via rebalance configuration overrides, fixed in 3.1.0.

CVE-2026-82432 (rated moderate) affects Apache Storm Nimbus (storm-server) versions 3.0.0 before 3.1.0. Nimbus validates topology.blobstore.map against the calling subject only at topology submission time. The rebalance operation accepts configuration overrides and strips a small set of keys but never re-runs that validation, so a caller authorized only to rebalance a topology can introduce an unauthorized blobstore map.

oss-securitySep 13, 14:30 UTC · 3d agoVulnerability CVE-2026-82432

From Megawatts to Tokens: How NVIDIA Maximizes AI Factory Production

NVIDIA detailed DSX power-management results: Lambda gained 24% token throughput at fixed power, and an AI factory auto-shed 1MW via Emerald AI's grid program.

NVIDIA says Lambda's first validation of DSX MaxLPS on HGX B200 servers ran 19 nodes within a 16-node power budget, lifting cluster token throughput 24% (roughly 4M to 5M tokens/second) and improving performance per watt by 23%. NVIDIA projects DSX MaxLPS can enable up to 40% more GPU capacity for Vera Rubin NVL72 factories within the same megawatt budget. Emerald AI's Conductor platform, running at NVIDIA's Eos factory with Silicon Valley Power, responded to over 200 utility demand signals, automatically dropping power from 4MW to 3MW without interrupting priority workloads. The first dedicated DSX Flex commercial deployment is planned at a 96-megawatt Manassas, Virginia facility.

NVIDIA BlogSep 15, 16:55 UTC · 1d agoAI industry

Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

TGOPD verifies teacher reliability per prompt before on-policy distillation, outperforming vanilla OPD across math, code, and instruction benchmarks.

Teacher-Gated On-Policy Distillation (TGOPD) estimates teacher reliability from verifier-scored teacher probes and routes each prompt either to dense on-policy distillation or to verifier-grounded GRPO, avoiding misleading updates from confidently wrong teachers under mode-seeking reverse KL. Across 4B and 35B students in mathematics, code, and instruction following, TGOPD outperforms vanilla OPD in all six single-domain settings and achieves higher seven-benchmark averages under multi-domain training. It also raises teacher-node GPU utilization from 9.8% to 78.9% in the measured 4B single-domain run by reusing idle teacher capacity.

Hugging Face daily papersSep 1, 20:00 UTC · 15d agoAI research

Harnessing LLMs for Automating BOLA Detection

Unit 42's BOLABuster methodology uses LLMs to automate detection of broken object-level authorization vulnerabilities, uncovering flaws in Grafana, Harbor, and Easy!Appointments.

Palo Alto Unit 42 details BOLABuster, a methodology combining large language models with heuristics to automate detection of broken object-level authorization (BOLA) flaws, which traditional fuzzing and static analysis struggle to find. The approach uses LLM reasoning to understand application logic, map endpoint dependency relationships, and generate and interpret test cases. It found CVE-2024-1313 in Grafana, CVE-2024-22278 in Harbor, and 15 CVEs in Easy!Appointments. The team is continuing to hunt for BOLAs in open-source and internal projects.

Palo Alto Unit 42Aug 17, 12:34 UTC · Aug 17, 2026Research CVE-2024-1313 CVE-2024-22278 CVE-2023-3285+14 CVEs