Injection, Attack and Erasure: Revocable Backdoor Attacks Via Machine Unlearning

Backdoor attacks pose a persistent security risk to deep neural networks DNNs due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that may be detect...

EUVD-2021-0449

Malware in sbrugna...

EUVD-2024-2430

Malicious code in bioql PyPI...

Towards Provable (In)Secure Model Weight Release Schemes

Recent secure weight release schemes claim to enable open-source model distribution while protecting model ownership and preventing misuse. However, these approaches lack rigorous security foundations and provide only informal security guarantees. Inspired by established works in cryptography, we...

CVE-2021-29553

TensorFlow is an end-to-end open source platform for machine learning. An attacker can read data outside of bounds of heap allocated buffer in tf.rawops.QuantizeAndDequantizeV3. This is because the...

CVE-2021-41221

TensorFlow is an open source platform for machine learning. In affected versions the shape inference code for the Cudnn operations in TensorFlow can be tricked into accessing invalid memory, via a heap buffer overflow. This occurs because the ranks of the input, inputh and inputc parameters are n...

CVE-2021-37670

TensorFlow is an end-to-end open source platform for machine learning. In affected versions an attacker can read from outside of bounds of heap allocated data by sending specially crafted illegal arguments to tf.rawops.UpperBound. The implementation does not validate the rank of sortedinput...

CVE-2023-27579 TensorFlow has Floating Point Exception in TFLite in conv kernel

TensorFlow is an end-to-end open source platform for machine learning. Constructing a tflite model with a paramater filterinputchannel of less than 1 gives a FPE. This issue has been patched in version 2.12. TensorFlow will also cherrypick the fix commit on TensorFlow 2.11.1...

Attacking Machine Learning Systems

The field of machine learning ML security--and corresponding adversarial ML--is rapidly advancing as researchers develop sophisticated techniques to perturb, disrupt, or steal the ML model or data. It’s a heady time; because we know so little about the security of these systems, there are many...

Inserting a Backdoor into a Machine-Learning System

Interesting research: "ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks, by Tim Clifford, Ilia Shumailov, Yiren Zhao, Ross Anderson, and Robert Mullins: Abstract: Early backdoor attacks against machine learning set off an arms race in attack and defence...

CVE-2022-35959 `CHECK` failures in `AvgPool3DGrad` in TensorFlow

TensorFlow is an open source platform for machine learning. The implementation of AvgPool3DGradOp does not fully validate the input originputshape. This results in an overflow that results in a CHECK failure which can be used to trigger a denial of service attack. We have patched the issue in...

CVE-2022-29193

TensorFlow is an open source platform for machine learning. Prior to versions 2.9.0, 2.8.1, 2.7.2, and 2.6.4, the implementation of tf.rawops.TensorSummaryV2 does not fully validate the input arguments. This results in a CHECK-failure which can be used to trigger a denial of service attack...

How we took part in MLSEC and (almost) won

This summer Kaspersky experts took part in the Machine Learning Security Evasion Competition MLSEC — a series of trials testing contestants ability to create and attack machine learning models. The event is comprised of two main challenges — one for attackers, and the other for defenders. The...

Attack AI systems in Machine Learning Evasion Competition

Today, we are launching MLSEC.IO, an educational Machine Learning Security Evasion Competition MLSEC for the AI and security communities to exercise their muscle to attack critical AI systems in a realistic setting. Hosted and sponsored by Microsoft, alongside NVIDIA, CUJO AI, VM-Ray, and MRG...

Google TensorFlow heap buffer overflow vulnerability (CNVD-2021-37648)

Google TensorFlow is an end-to-end open source machine learning platform. A heap buffer overflow vulnerability exists in tf.rawops.FractionalAvgPoolGrad in Google TensorFlow. No detailed vulnerability details are provided at this time...

New Framework Released to Protect Machine Learning Systems From Adversarial Attacks

Microsoft, in collaboration with MITRE, IBM, NVIDIA, and Bosch, has released a new open framework that aims to help security analysts detect, respond to, and remediate adversarial attacks against machine learning ML systems. Called the Adversarial ML Threat Matrix, the initiative is an attempt to...