Google-Tensor-Chips

Google Tensor Chips — DarWINN NPU Access Direct-access tooling for the Google Tensor NPU DarWINN, reverse-engineered across two generations: Tensor G2 Pixel 7, codename Janeiro and Tensor G3 Pixel 8, codename Rio. Why this exists I was trying to get LLM inference running on the phone and wanted t...

CVE-2026-34159-Vulnerability-Research-Analysis-Detection

CVE-2026-34159-취약점-연구-분석-탐지 deserializetensor의 치명적인 버퍼 검증 우회 llama.cpp b8492. Null 텐서 버퍼가 경계 검사를 건너뛰어 GRAPHCOMPUTE를 통한 인증 없는 임의 읽기/쓰기를 가능하게 합니다. ASLR 우회 + TCP 50052를 통한 RCE. 포함 내용: 기술 분석 및 익스플로잇 체인 전체 Wireshark PCAP HELLO→BUFFERCLEAR Suricata/Snort 시그니처 랩 재현 Windows b8487 + WSL PoC 탐지/완화 전략...

CVE-2026-7020

CVE-2026-7020 Ollama의 tensor digest 경로 탐색을 통한 임의 파일 읽기 취약점. 인증 없이 세 번의 API 호출만으로 접근 가능한 Ollama 호스트에서 SSH 호스트 키및 기타 모든 파일를 유출합니다. Writeup: 공동 연구자 @gouldnicholas 사용법 python3 poc.py 알려진 크기의 세 가지 SSH 호스트 키 유형을 모두 시도하고 캡처된 내용을 출력합니다. CVE CVE-2026-7020...

CVE-2026-85228

A flaw was found in Deep Java Library. Due to an integer overflow during tensor buffer validation, a remote, unauthenticated attacker can send a crafted tensor payload to trigger out-of-bounds memory access. Successful exploitation can allow an attacker to obtain sensitive data from adjacent...

EUVD-2026-88961

NVIDIA DeepStream contains a vulnerability where an attacker could cause an integer overflow by supplying crafted tensor dimensions in a YAML configuration file. A successful exploit of this vulnerability might lead to denial of service, information disclosure, data tampering...

CVE-2026-65102: Integer Overflow or Wraparound

NVIDIA DeepStream contains a vulnerability where an attacker could cause an integer overflow by supplying crafted tensor dimensions in a YAML configuration file. A successful exploit of this vulnerability might lead to denial of service, information disclosure, data tampering...

CVE-2026-100652

vLLM versions 0.22.0 through 0.23.0 fail to validate stoptokenids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with mintokens greater than zero and out-of-vocabulary stoptokenids to...

EUVD-2026-87746

vLLM versions 0.22.0 through 0.23.0 fail to validate stoptokenids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with mintokens greater than zero and out-of-vocabulary stoptokenids to...

CVE-2026-100652

vLLM versions 0.22.0 through 0.23.0 are vulnerable to a Denial of Service (DoS) due to a lack of validation for stop_token_ids in the Rust HTTP and gRPC frontends . If an attacker submits requests with min_tokens greater than zero and out-of-vocabulary token IDs, the values reach the MinTokensLog...

CVE-2026-100652 vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

vLLM versions 0.22.0 through 0.23.0 fail to validate stoptokenids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with mintokens greater than zero and out-of-vocabulary stoptokenids to...

CVE-2026-100652 vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

vLLM versions 0.22.0 through 0.23.0 fail to validate stoptokenids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with mintokens greater than zero and out-of-vocabulary stoptokenids to...

CVE-2026-100652: Improper Input Validation

vLLM versions 0.22.0 through 0.23.0 fail to validate stoptokenids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with mintokens greater than zero and out-of-vocabulary stoptokenids to...

Improper Validation of Array Index

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Improper Validation of Array Index via the stoptokenids and allowedtokenids parameters in vllm/samplingparams.py, which are not validated against th...

CVE-2026-85180

A flaw was found in Ollama. This vulnerability, known as Server-Side Request Forgery SSRF, occurs because Ollama fails to validate redirect destinations when pulling tensor-layer models. An unauthenticated attacker can exploit this by controlling a registry and serving a malicious tensor-layer...

CVE-2026-55093 tract-nnef: integer overflow in NNEF `.dat` tensor parser yields an out-of-bounds read on model load

Tract is a tiny, no-nonsense, self-contained TensorFlow and ONNX inference toolkit. Prior to 0.21.16, 0.22.2, and 0.23.1, tract-nnef uses unchecked usize multiplication in nnef/src/tensors.rs readtensor for attacker-controlled tensor dimensions, the allocation size, and the reported tensor length...

CVE-2026-55093 tract-nnef: integer overflow in NNEF `.dat` tensor parser yields an out-of-bounds read on model load

Tract is a tiny, no-nonsense, self-contained TensorFlow and ONNX inference toolkit. Prior to 0.21.16, 0.22.2, and 0.23.1, tract-nnef uses unchecked usize multiplication in nnef/src/tensors.rs readtensor for attacker-controlled tensor dimensions, the allocation size, and the reported tensor length...

CVE-2026-85228

An integer overflow in the tensor buffer validation component in Amazon Deep Java Library DJL from 0.13.0 through 0.36.0 on all platforms might allow a remote unauthenticated actor to obtain information from adjacent process memory or cause a denial of service via a crafted tensor payload. To...

CVE-2026-85228 Integer overflow in tensor buffer validation in Deep Java Library

An integer overflow in the tensor buffer validation component in Amazon Deep Java Library DJL from 0.13.0 through 0.36.0 on all platforms might allow a remote unauthenticated actor to obtain information from adjacent process memory or cause a denial of service via a crafted tensor payload. To...

CVE-2026-85228

An integer overflow in the tensor buffer validation component of Amazon Deep Java Library (DJL) versions 0.13.0 through 0.36.0 (all platforms) allows a remote unauthenticated actor to read information from adjacent process memory or trigger a denial of service by submitting a crafted tensor paylo...

CVE-2026-85228 Integer overflow in tensor buffer validation in Deep Java Library

An integer overflow in the tensor buffer validation component in Amazon Deep Java Library DJL from 0.13.0 through 0.36.0 on all platforms might allow a remote unauthenticated actor to obtain information from adjacent process memory or cause a denial of service via a crafted tensor payload. To...