Lucene search
+L

250 matches found

Kitploit
Kitploit
•added 2026/10/07 1:23 p.m.•20 views

alibi-detect

Alibi Detect は、倖れ倀 、敵察的 、ドリフト 怜出に特化した゜ヌス利甚可胜な Python ラむブラリです。このパッケヌゞは、衚圢匏デヌタ、テキスト、画像、時系列向けのオンラむンおよびオフラむン怜出噚の䞡方をカバヌするこずを目的ずしおいたす。ドリフト怜出では、TensorFlow ず PyTorch の䞡バック゚ンドがサポヌトされおいたす。 ドキュメント 本番環境での倖れ倀ず分垃のモニタリングの重芁性に関する背景に぀いおは、論文 Monitoring and explainability of models in production に基づき、Alibi Detect...

6AI score
SaveExploits0References4
Kitploit
Kitploit
•added 2026/10/07 11:46 a.m.•23 views

LID

██╗ ██╗██████╗ ██║ ██║██╔══██╗ ██║ ██║██║ ██║ ██║ ██║██║ ██║ ███████╗██║██████╔╝ ╚══════╝╚═╝╚═════╝ Linux Integrity Drift — 「Linuxは死にかけおいる」 — LSMのセキュリティ保蚌を迂回するカヌネルコヌドパスの䜓系的な発芋 門は砎られたのではない。迂回されたのだ。 LIDずは䜕か Linux Security Moduleフレヌムワヌクには、20幎以䞊 にわたっお維持されおきた䞭栞的な保蚌が1぀ありたす セキュリティモゞュヌルは制限を远加...

6AI score
SaveExploits0References5
Kitploit
Kitploit
•added 2026/10/07 8:46 a.m.•24 views

drift-node-sdk

Node.js Tusk Drift SDKは、サヌビスずの間でやり取りされるAPI呌び出しをキャプチャしおリプレむするこずで、高速か぀決定論的なAPIテストを可胜にしたす。実際のAPI呌び出しを自動的に蚘録し、Tusk CLIを䜿甚しおテストずしおリプレむし、リグレッションを怜出したす。リプレむ䞭は、すべおの送信リク゚ストが蚘録されたデヌタでむンタヌセプトされ、副䜜甚なしに䞀貫した動䜜が保蚌されたす。 デモリポゞトリで詊す → ドキュメント 包括的なガむドずAPIリファレンスに぀いおは、完党なドキュメントをご芧ください。 SDKガむド 初期化ガむド -...

6AI score
SaveExploits0References10
Kitploit
Kitploit
•added 2026/10/07 5:05 a.m.•23 views

drift-corpus

Drift Corpus: Ring 0 Drift Corpus 는 Windows 컀널 팚치 diff의 권위 있는 였픈 소슀 저장소입니닀. 읎 아티팩튞는 ByteRay의 자동 늬버슀 엔지니얎링 엔진읎자 Argus-Systems 플랫폌의 음부읞 Drift Agent 륌 사용하여 생성됩니닀. Drift륌 통핎 Microsoft가 팚치한 Windows 컀널 췚앜점을 성공적윌로 맀핑, 분석 및 죌석 처늬했습니닀. 현재 컬렉션은 2026년 항목240개 읎상을 포핚하며, 시간읎 지낚에 따띌 추가 항목읎 추가되고 있습니닀. 🚀 컀뮀니티 Der...

6.1AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/10/06 8:41 p.m.•21 views

ClientInspectorV2

ClientInspectorv2 소개 당신읎 통제하고 있습니까? - 아니멎 팚치, 안티바읎러슀, BitLocker 활성화 같은 핵심 읞프띌 프로섞슀가 표류하고 있습니까? 또는 고꞉ 읞벀토늬 륌 수행하여 Lenovo 또는 Dell 볎슝 상태륌 조회하고 싶닀멎 계속 읜얎볎섞요. ClientInspector 륌 확읞핎 볎섞요. 읎 도구는 완전한 큎띌읎얞튞 환겜 에 대한 탁월한 통찰력 을 얻는 데 도움을 쀍니닀. ClientInspector는 컀뮀니티에 묎료 로 제공됩니닀. Azure 로귞 수집 파읎프띌읞 , Azure 데읎터 수집...

6.3AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/10/06 4:55 a.m.•13 views

Rubrics-as-an-Attack-Surface

攻撃察象ずしおのルヌブリック: LLM審査員におけるステルスな遞奜ドリフト 📊 デヌタセット • 🀖 孊習枈みモデル • 📝 論文 • 💻 リポゞトリ このリポゞトリには、Ruomeng Ding、Yifei Pang、He Sun、Yizhong Wang、Steven Wu、Zhun Dengによる論文攻撃察象ずしおのルヌブリック: LLM審査員におけるステルスな遞奜ドリフトのコヌドが含たれおいたす。...

6.3AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/10/05 1:44 p.m.•14 views

clawguard

🊞 ClawGuard v3 ゚ンタヌプラむズAI゚ヌゞェントセキュリティツヌルキット - SKILL.md駆動型アクティブディフェンス 栞心理念 ClawGuard v3の防埡の䞭栞はコヌドではなく、SKILL.mdにありたす 各モゞュヌルのSKILL.md自䜓が完党な防埡ガむドです ゚ヌゞェントにい぀トリガヌするか を指瀺 ゚ヌゞェントにどのように怜出するか をガむド 具䜓的な怜出パタヌンずルヌル を提䟛 出力圢匏ず刀断基準 を定矩 コヌドスクリプトは補助ツヌルに過ぎず、本圓の知性はSKILL.mdにありたす。 🎯 5぀のセキュリティモゞュヌル モゞュヌル| 䜍眮|...

6.2AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/10/05 7:42 a.m.•12 views

Adaptive_Greedy_Local_Search

Adaptive Greedy Local Search AGLS 意味保存型プロンプトハむゞャック自動プロンプト最適化に察するブラックボックス敵察的攻撃ICME 2026 抂芁...

6.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/03 12:00 a.m.•5 views

Invisible Ink, Visible Lies: How Production Watermarking Causes LLMs to Hallucinate

Text watermarking helps identify AI-generated content, but its effect on factual reliability remains underexplored. In this paper, we study watermarking hallucination: factual errors induced or amplified by watermarking even when the required evidence is present in the context and the unwatermark...

SaveExploits0
Kitploit
Kitploit
•added 2026/10/01 8:14 p.m.•12 views

BIDO

BIDO このコヌドは「BIDO: A Unified Approach to Address Obfuscation and Concept Drift Challenges in Image-based Malware Detection」に属するものです。 著者 著者: Junhui Li1、Chengbin Feng2、Zhiwei Yang1、Qi Mo1、Wei Wang1。 所属機関 所属機関1Software School, Yunnan University雲南倧孊゜フトりェア孊院、䞭囜雲南省昆明垂 650091。 所属機関2School of...

6AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/10/01 7:21 p.m.•16 views

safety-awareness

クロスモヌダル安党性ドリフトのための転移安党性認識 マルチモヌダル倧芏暡蚀語モデルにおけるクロスモヌダル安党性ドリフトのための転移安党性認識 EMNLP 2026 Findingsの公匏実装です。 このリポゞトリには、Qwen3-VLの安党性認識方向パむプラむンが含たれおいたす。有害および無害なマルチモヌダル事䟋から拒吊関連の掻性化方向を抜出し、良性タスクのドリフトを制限しながら拒吊行動を改善する方向を遞択し、必芁に応じお方向固有の安党性認識ベクトルを蚓緎したす。 このコヌドは珟圚、Hugging Face...

6.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/01 12:00 a.m.•10 views

Homomorphic Advantage Operator: Stabilizing Reinforcement Learning under Fully Homomorphic Encryption Constraints

Privacy-preserving machine learning presents significant deployment challenges on the cloud for intelligent systems with confidential data. Fully Homomorphic Encryption FHE offers a compelling solution for secure computation, preserving data confidentiality of cloud computations. However, applyin...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/01 12:00 a.m.•10 views

Learnt Attacks on Quantum Key Distribution under Channel Noise and Device Drift

Quantum key distribution QKD links are provisioned from security analyses of stationary channels, whereas the devices that determine the channel drift between recalibrations. Whether an eavesdropper who cannot alter the channel's own noise gains by following that drift has not been quantified...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/09/29 12:00 a.m.•6 views

Proof-Gated Signing: Solver-Checked Transaction Guards That Hold under State Drift for Onchain AI Agents

AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of defense is a pre-signing check: a static allowlist, an LLM reviewer, or a transaction simulation. All three share a gap: the check describes the chain...

6.1AI score
SaveExploits0
OSV
OSV
•added 2026/09/04 6:17 p.m.•10 views

AZL-99609 CVE-2026-80893 affecting package kernel for versions less than 6.6.152.1-1

In the Linux kernel, the following vulnerability has been resolved: mm/hugetlb: fix swap entry corruption when clearing uffd-wp at fork copyhugetlbpagerange clears the uffd-wp bit of migration and hwpoison entries with hugepteclearuffdwp, which operates on the present-PTE bit position. Swap entri...

6AI score0.00215EPSS
SaveExploits0References1
Kitploit
Kitploit
•added 2026/09/03 3:41 p.m.•15 views

sbomlyze v0.5.3

sbomlyze git diff for your SBOM. Compare two Software Bills of Materials and see what changed between builds, versions, and releases. sbomlyze compares component hashes, not only version strings. When an attacker swaps a package without bumping its version, sbomlyze flags it. Generators and...

6.2AI score
SaveExploits0References10
NVD
NVD
•added 2026/08/31 9:17 a.m.•24 views

CVE-2026-82858

@hulumi/drift versions before 1.3.2 accept externally supplied execute plans without sufficient provenance validation, allowing untrusted reconciliation input to be treated as trusted. Attackers can supply malicious execute plans that bypass security checks to perform unsafe reconciliation...

9.8CVSS0.00285EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/08/31 8:46 a.m.•13 views

EUVD-2026-68446

@hulumi/drift versions before 1.3.2 accept externally supplied execute plans without sufficient provenance validation, allowing untrusted reconciliation input to be treated as trusted. Attackers can supply malicious execute plans that bypass security checks to perform unsafe reconciliation...

9.8CVSS5.9AI score0.00285EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/08/31 8:46 a.m.•45 views

CVE-2026-82858 @hulumi/drift before 1.3.2 Unsafe Execute Plan Acceptance

@hulumi/drift versions before 1.3.2 accept externally supplied execute plans without sufficient provenance validation, allowing untrusted reconciliation input to be treated as trusted. Attackers can supply malicious execute plans that bypass security checks to perform unsafe reconciliation...

9.8CVSS0.00285EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
•added 2026/08/31 8:46 a.m.•16 views

CVE-2026-82858 @hulumi/drift before 1.3.2 Unsafe Execute Plan Acceptance

@hulumi/drift versions before 1.3.2 accept externally supplied execute plans without sufficient provenance validation, allowing untrusted reconciliation input to be treated as trusted. Attackers can supply malicious execute plans that bypass security checks to perform unsafe reconciliation...

9.8CVSS5.9AI score0.00285EPSS
SaveExploits0References2
Rows per page
Query Builder