Lucene search
K

28 matches found

Packet Storm News
Packet Storm News
added 2026/05/20 12:0 a.m.5 views

Detecting Trojaned DNNs Via Spectral Regression Analysis

Modern DNNs are repeatedly fine-tuned to incorporate new data and functionality. This evolutionary workflow introduces a security risk when updated data cannot be fully trusted, as adversaries may implant Trojans during fine-tuning. We present MIST, a Trojan detection approach that analyzes how a...

5.8AI score
Exploits0
AstraLinux
AstraLinux
added 2026/05/03 11:59 p.m.4 views

Astra Linux - уязвимость в logback

A serialization vulnerability in the logback receiver component, as part of logback version 1.4.11, allows an attacker to carry out a Denial-of-Service attack by sending poisoned data...

7.5CVSS6.8AI score0.0063EPSS
Exploits0References1
SUSE CVE
SUSE CVE
added 2025/10/05 2:57 a.m.3 views

SUSE CVE-2023-6378

A serialization vulnerability in logback receiver component part of logback version 1.4.11 allows an attacker to mount a Denial-Of-Service attack by sending poisoned data...

7.5CVSS7.2AI score0.0063EPSS
Exploits0References2
EUVD
EUVD
added 2025/10/03 8:7 p.m.1 views

EUVD-2023-3212

Malicious code in bioql PyPI...

7.5CVSS6.9AI score0.00224EPSS
Exploits0References6
EUVD
EUVD
added 2025/10/03 8:7 p.m.0 views

EUVD-2023-3046

Malicious code in bioql PyPI...

7.5CVSS7AI score0.0063EPSS
Exploits0References10
Trend Micro Simply Security
Trend Micro Simply Security
added 2025/09/24 12:0 a.m.4 views

This Is How Your LLM Gets Compromised

Poisoned data. Malicious LoRAs. Trojan model files. AI attacks are stealthier than ever—often invisible until it’s too late. Here’s how to catch them before they catch you...

7AI score
Exploits0
Packet Storm News
Packet Storm News
added 2025/07/07 12:0 a.m.2 views

CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation

Deep Neural Networks DNNs are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computational costs or low effectiveness against advanced attacks like clean-label and...

6.8AI score
Exploits0
Packet Storm News
Packet Storm News
added 2025/05/28 12:0 a.m.3 views

Machine Learning Models Have a Supply Chain Problem

Powerful machine learning ML models are now readily available online, which creates exciting possibilities for users who lack the deep technical expertise or substantial computing resources needed to develop them. On the other hand, this type of open ecosystem comes with many risks. In this paper...

6.9AI score
Exploits0
Packet Storm News
Packet Storm News
added 2025/05/13 12:0 a.m.2 views

Where the Devil Hides: Deepfake Detectors Can No Longer Be Trusted

With the advancement of AI generative techniques, Deepfake faces have become incredibly realistic and nearly indistinguishable to the human eye. To counter this, Deepfake detectors have been developed as reliable tools for assessing face authenticity. These detectors are typically developed on De...

7.2AI score
Exploits0
Packet Storm News
Packet Storm News
added 2025/04/30 12:0 a.m.2 views

How to Backdoor the Knowledge Distillation

Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more efficient student model. Traditionally, this process is regarded as secure, assuming the teacher model is clean. This...

7.3AI score
Exploits0
RedHat Linux
RedHat Linux
added 2024/05/23 10:45 p.m.1 views

logback: serialization vulnerability in logback receiver

A flaw was found in the logback package, where it is vulnerable to a denial of service caused by a serialization flaw in the receiver component. By sending specially crafted poisoned data, a remote attacker can cause a denial of service condition...

7.5CVSS7.2AI score0.0063EPSS
Exploits0References4
RedHat Linux
RedHat Linux
added 2024/05/23 10:45 p.m.2 views

logback: A serialization vulnerability in logback receiver

A flaw was found in the logback package. Affected versions of this package are vulnerable to Uncontrolled Resource Consumption 'Resource Exhaustion' via the logback receiver component. This flaw allows an attacker to mount a denial-of-service attack by sending poisoned data...

7.5CVSS7.1AI score0.00224EPSS
Exploits0References4
RedHat Linux
RedHat Linux
added 2024/05/21 2:18 p.m.1 views

logback: A serialization vulnerability in logback receiver

A flaw was found in the logback package. Affected versions of this package are vulnerable to Uncontrolled Resource Consumption 'Resource Exhaustion' via the logback receiver component. This flaw allows an attacker to mount a denial-of-service attack by sending poisoned data...

7.5CVSS7.1AI score0.00224EPSS
Exploits0References4
RedHat Linux
RedHat Linux
added 2024/05/21 2:18 p.m.1 views

logback: serialization vulnerability in logback receiver

A flaw was found in the logback package, where it is vulnerable to a denial of service caused by a serialization flaw in the receiver component. By sending specially crafted poisoned data, a remote attacker can cause a denial of service condition...

7.5CVSS7.2AI score0.0063EPSS
Exploits0References4
RedHat Linux
RedHat Linux
added 2024/02/12 6:1 p.m.1 views

logback: A serialization vulnerability in logback receiver

A flaw was found in the logback package. Affected versions of this package are vulnerable to Uncontrolled Resource Consumption 'Resource Exhaustion' via the logback receiver component. This flaw allows an attacker to mount a denial-of-service attack by sending poisoned data...

7.5CVSS7.1AI score0.00224EPSS
Exploits0References4
RedHat Linux
RedHat Linux
added 2024/02/12 6:1 p.m.1 views

logback: serialization vulnerability in logback receiver

A flaw was found in the logback package, where it is vulnerable to a denial of service caused by a serialization flaw in the receiver component. By sending specially crafted poisoned data, a remote attacker can cause a denial of service condition...

7.5CVSS7.2AI score0.0063EPSS
Exploits0References4
HackRead
HackRead
added 2024/01/08 1:22 p.m.8 views

Poisoned Data, Malicious Manipulation: NIST Study Reveals AI Vulnerabilities

By Waqas NIST Unveils Insights on AI Vulnerabilities and Potential Threats.w This is a post from HackRead.com Read the original post: Poisoned Data, Malicious Manipulation: NIST Study Reveals AI Vulnerabilities...

7.4AI score
Exploits0
OSV
OSV
added 2023/12/22 11:6 a.m.2 views

OESA-2023-1946 logback security update

Logback is intended as a successor to the popular log4j project. Security Fixes: A serialization vulnerability in logback receiver component part of logback version 1.4.11 allows an attacker to mount a Denial-Of-Service attack by sending poisoned data. CVE-2023-6378 A serialization vulnerability ...

7.5CVSS8.9AI score0.0063EPSS
Exploits0References3
RedhatCVE
RedhatCVE
added 2023/12/05 12:43 p.m.102 views

CVE-2023-6378

A flaw was found in the logback package, where it is vulnerable to a denial of service caused by a serialization flaw in the receiver component. By sending specially crafted poisoned data, a remote attacker can cause a denial of service condition. Mitigation Mitigation for this issue is either no...

7.5CVSS6.8AI score0.0063EPSS
Exploits0References3
OSV
OSV
added 2023/12/04 9:30 a.m.0 views

GHSA-GM62-RW4G-VRC4 Logback is vulnerable to an attacker mounting a Denial-Of-Service attack by sending poisoned data

A serialization vulnerability in logback receiver component part of logback version 1.4.13, 1.3.13 and 1.2.12 allows an attacker to mount a Denial-Of-Service attack by sending poisoned data...

7.1CVSS7.2AI score0.00224EPSS
Exploits0References6
Rows per page
Query Builder