Lucene search
+L

578 matches found

Kitploit
Kitploit
•added 2026/11/16 7:57 p.m.•30 views

SEVulDet

SEVulDet SEVulDet is a semantics-enhanced deep learning-based framework that can accurately pinpoint vulnerability patterns by extracting, preserving, and learning more semantics. E-mail for communication: [email protected] Details of SEVulDet Recent years have seen increased attention to de...

5.5CVSS7.7AI score0.0042EPSS
SaveExploits0
Kitploit
Kitploit
•added 2026/11/15 8:46 a.m.•61 views

D-Scan

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse Official implementation of SIGIR 2026 paper When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse. D-SCAN is an analysis framework for detecting document poisoning attacks in RAG...

6.3AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/11/14 3:22 p.m.•28 views

attack-attention

Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks Official PyTorch implementation of the paper "Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks" , accepted in the Adversarial Machine Learning on Computer Vision: Foundation Models + X ADV...

6.3AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/11/14 8:39 a.m.•24 views

Sec5GLoc

Sec5GLoc: Securing 5G Indoor Localization via Adversary-Resilient Deep Learning Architecture Our work addresses security and privacy challenges in 5G indoor localization by proposing an adversary-resilient deep learning architecture. Sec5GLoc combines Channel Impulse Response CIR fingerprinting...

6.2AI score
SaveExploits0
osv_ghsa
osv_ghsa
•added 2026/10/28 9:15 p.m.•16 views

GHSA-8397-8QF6-F2GM vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine

Summary The Phi-4 multimodal audio encoder phi4mmaudio.py / phi4mmutils.py runs its conformer attention in eager mode by default: the official HF config of microsoft/Phi-4-multimodal-instruct does not set useptscaleddotproductattention, so the default False applies phi4mmaudio.py:166, :876;...

6.5CVSS6.2AI score0.00329EPSS
SaveExploits1References6
Packet Storm News
Packet Storm News
•added 2026/10/27 12:00 a.m.•14 views

Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness

We introduce Heads of Security HoS, a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates. HoS learns how each head should redistribute attention between trusted and untrusted tokens, enabling models to reason over untrusted conte...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/21 12:00 a.m.•28 views

Parameters Efficient Language Model with Latent Cross-Attention for IoT Intrusion Detection

Language models have shown strong potential for intrusion detection, but their high memory and computational demands make them difficult to deploy in resource-constrained IoT environments. In this work, we propose a compact Transformer-based architecture that compresses the input into a small...

5.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/13 12:00 a.m.•16 views

Are You Reading the Right Thing? Rethinking Internal Signals for Prompt-Injection Detection

Several recent studies propose detecting prompt injections from a language model's internal state. However, these methods do not measure a single security property. Residual-stream probes, attention scores, role projections, exposure probes, and concept readouts may capture injection presence,...

5.9AI score
SaveExploits0
NVD
NVD
•added 2026/10/08 3:17 p.m.•40 views

CVE-2026-93034

SGLang contains an arbitrary code execution vulnerability caused by the ZMQ message decoder unconditionally deserializing PickleWrapper payloads via pickle.loads in maybeunwrappickle without type allowlisting or authentication; this vulnerability persists via the msgpack path even when...

9.8CVSS0.0046EPSS
SaveExploits0References2
Mend
Mend
•added 2026/10/08 2:00 p.m.•17 views

CVE-2026-93034

SGLang contains an arbitrary code execution vulnerability caused by the ZMQ message decoder unconditionally deserializing PickleWrapper payloads via pickle.loads in maybeunwrappickle without type allowlisting or authentication; this vulnerability persists via the msgpack path even when...

9.8CVSS6.4AI score0.0046EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/10/08 2:00 p.m.•64 views

CVE-2026-93034 CVE-2026-93034

SGLang contains an arbitrary code execution vulnerability caused by the ZMQ message decoder unconditionally deserializing PickleWrapper payloads via pickle.loads in maybeunwrappickle without type allowlisting or authentication; this vulnerability persists via the msgpack path even when...

0.0046EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
•added 2026/10/08 2:00 p.m.•23 views

CVE-2026-93034 CVE-2026-93034

SGLang contains an arbitrary code execution vulnerability caused by the ZMQ message decoder unconditionally deserializing PickleWrapper payloads via pickle.loads in maybeunwrappickle without type allowlisting or authentication; this vulnerability persists via the msgpack path even when...

6.4AI score0.0046EPSS
SaveExploits0References2
CVE
CVE
•added 2026/10/08 2:00 p.m.•83 views

CVE-2026-93034

SGLang is affected by an arbitrary code execution vulnerability originating from the ZMQ message decoder . The root cause is the unconditional deserialization of PickleWrapper payloads using pickle.loads() within the _maybe_unwrap_pickle function, which lacks type allowlisting or authentication. ...

9.8CVSS6.4AI score0.0046EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/10/08 2:00 p.m.•39 views

EUVD-2026-94989

SGLang contains an arbitrary code execution vulnerability caused by the ZMQ message decoder unconditionally deserializing PickleWrapper payloads via pickle.loads in maybeunwrappickle without type allowlisting or authentication; this vulnerability persists via the msgpack path even when...

9.8CVSS6.4AI score0.0046EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/10/08 12:00 a.m.•22 views

PT-2026-108017

Name of the Vulnerable Software and Affected Versions SGLang affected versions not specified Description An arbitrary code execution issue exists due to the ZMQ message decoder unconditionally deserializing PickleWrapper payloads using the pickle.loads function within maybe unwrap pickle without...

9.8CVSS6.4AI score0.0046EPSS
SaveExploits0References6
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/10/08 12:00 a.m.•14 views

CVE-2026-93034: Deserialization of Untrusted Data

SGLang contains an arbitrary code execution vulnerability caused by the ZMQ message decoder unconditionally deserializing PickleWrapper payloads via pickle.loads in maybeunwrappickle without type allowlisting or authentication; this vulnerability persists via the msgpack path even when...

9.8CVSS6.4AI score0.0046EPSS
SaveExploits0References2
Packet Storm News
Packet Storm News
•added 2026/10/03 12:00 a.m.•22 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...

5.9AI score
SaveExploits0
Vulnrichment
Vulnrichment
•added 2026/09/23 6:00 a.m.•23 views

CVE-2026-91073 Subscribe Forms 1.4.1 - 1.6.2 - Author+ Stored XSS via Attention Effect Form Setting

The Subscribe Forms WordPress plugin before 1.6.3 does not sanitise and escape one of its form settings before outputting it in a page, allowing authenticated users with the Author role and above to perform Stored Cross-Site Scripting attacks that execute in the browser of any visitor who views a...

6AI score0.00431EPSS
SaveExploits0References1
Cvelist
Cvelist
•added 2026/09/23 6:00 a.m.•47 views

CVE-2026-91073 Subscribe Forms 1.4.1 - 1.6.2 - Author+ Stored XSS via Attention Effect Form Setting

The Subscribe Forms WordPress plugin before 1.6.3 does not sanitise and escape one of its form settings before outputting it in a page, allowing authenticated users with the Author role and above to perform Stored Cross-Site Scripting attacks that execute in the browser of any visitor who views a...

0.00431EPSS
SaveExploits0References1
CVE
CVE
•added 2026/09/23 6:00 a.m.•34 views

CVE-2026-91073

The Subscribe Forms WordPress plugin (versions 1.4.1-1.6.2 ) is vulnerable to a Stored Cross-Site Scripting (XSS) attack. The root cause is the failure to properly sanitise and escape specific form settings before they are outputted on a page. This allows authenticated users with the Author role ...

6.8CVSS6AI score0.00431EPSS
SaveExploits0References1
Rows per page
Query Builder