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...

Navigating the Deep: Signature Extraction on Deep Neural Networks

Neural network model extraction has emerged in recent years as an important security concern, as adversaries attempt to recover a network's parameters via black-box queries. A key step in this process is signature extraction, which aims to recover the absolute values of the network's weights laye...

TED-LaST: Towards Robust Backdoor Defense against Adaptive Attacks

Deep Neural Networks DNNs are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior. Topological Evolution Dynamics TED has recently emerged as a powerful tool for detecting backdoor attacks in DNNs. However, TED can be...

TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks

Verification of the integrity of deep learning inference is crucial for understanding whether a model is being applied correctly. However, such verification typically requires access to model weights and potentially sensitive or private training data. So-called Zero-knowledge Succinct...

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

Deep Neural Networks DNNs have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target model -- often trained with subsets of the target model's traini...

cifar-10-model (=7.4.0), clip-jax (>=0.0.1 <=0.0.4) +9 more potentially affected by CVE-2023-33976 via tensorflow-cpu (>=1.15.0 <=2.11.1)

tensorflow-cpu PYPI version =1.15.0, =0.0.1, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-33976 Source advisory: OSV:GHSA-GJH7-XX4R-X345...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25659 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25659 Source advisory: OSV:GHSA-93VR-9Q9M-PJ8P...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25660 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25660 Source advisory: OSV:GHSA-QJQC-VQCF-5QVJ...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25663 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25663 Source advisory: OSV:GHSA-64JG-WJWW-7C5W...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25664 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25664 Source advisory: OSV:GHSA-6HG6-5C2Q-7RCR...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25665 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25665 Source advisory: OSV:GHSA-558H-MQ8X-7Q9G...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25670 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25670 Source advisory: OSV:GHSA-49RQ-HWC3-X77W...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25672 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25672 Source advisory: OSV:GHSA-94MM-G2MV-8P7R...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25673 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25673 Source advisory: OSV:GHSA-647V-R7QQ-24FH...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25674 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25674 Source advisory: OSV:GHSA-GF97-Q72M-7579...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25675 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25675 Source advisory: OSV:GHSA-7X4V-9GXG-9HWJ...

cifar-10-model (=7.4.0), gamornet-cpu (>=0.2.3 <=0.4.3) +8 more potentially affected by CVE-2023-25658 via tensorflow-cpu (>=1.15.0 <=2.11.0)

tensorflow-cpu PYPI version =1.15.0, =0.2.3, =0.0.5, =1.0.0, =1.8.2, =0.1.3, =0.3.0.dev221212, =0.7.0, =0.7.5 Source cves: CVE-2023-25658 Source advisory: OSV:GHSA-68V3-G9CM-RMM6...

aiproteomics (=0.2.1), alpharing (>=1.0.0 <=2.0.0) +25 more potentially affected by CVE-2021-29616 via tensorflow-cpu (>=1.15.0 <=2.1.0)

tensorflow-cpu PYPI version =1.15.0, =1.0.0, =0.0.1, =1.0.0.4, =0.1.0, =0.2.3, =0.0.5, =0.1.2, =1.0.0, =1.8.2, =1.6.1, =1.8.3 - netfl =1.5.0 and more Source cves: CVE-2021-29616 Source advisory: OSV:GHSA-4HVV-7X94-7VQ8...

aiproteomics (=0.2.1), alpharing (>=1.0.0 <=2.0.0) +25 more potentially affected by CVE-2021-29608 via tensorflow-cpu (>=1.15.0 <=2.1.0)

tensorflow-cpu PYPI version =1.15.0, =1.0.0, =0.0.1, =1.0.0.4, =0.1.0, =0.2.3, =0.0.5, =0.1.2, =1.0.0, =1.8.2, =1.6.1, =1.8.3 - netfl =1.5.0 and more Source cves: CVE-2021-29608 Source advisory: OSV:GHSA-RGVQ-PCVF-HX75...

aiproteomics (=0.2.1), alpharing (>=1.0.0 <=2.0.0) +25 more potentially affected by CVE-2021-29604 via tensorflow-cpu (>=1.15.0 <=2.1.0)

tensorflow-cpu PYPI version =1.15.0, =1.0.0, =0.0.1, =1.0.0.4, =0.1.0, =0.2.3, =0.0.5, =0.1.2, =1.0.0, =1.8.2, =1.6.1, =1.8.3 - netfl =1.5.0 and more Source cves: CVE-2021-29604 Source advisory: OSV:GHSA-8RM6-75MF-7R7R...