107 matches found
MAL-2025-9019 Malicious code in @malware-test-toxic-cubeb/test-mlw3-toxic-cubeb (npm)
The package @malware-test-toxic-cubeb/test-mlw3-toxic-cubeb was found to contain malicious code...
Malicious code in test-mlw1-toxic-cubeb (npm)
The package test-mlw1-toxic-cubeb was found to contain malicious code...
MAL-2025-34814 Malicious code in test-mlw1-toxic-cubeb (npm)
The package test-mlw1-toxic-cubeb was found to contain malicious code...
Malicious code in test-mlw2-toxic-cubeb (npm)
The package test-mlw2-toxic-cubeb was found to contain malicious code...
MAL-2025-36485 Malicious code in test-mlw2-toxic-cubeb (npm)
The package test-mlw2-toxic-cubeb was found to contain malicious code...
IF-GUIDE: Influence Function-Guided Detoxification of LLMs
We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained and potentially toxic models to align them with human values. In contrast, we propose a...
Friday Squid Blogging: Pyjama Squid
The small pyjama squid Sepioloidea lineolata produces toxic slime, "a rare example of a poisonous predatory mollusc." As usual, you can also use this squid post to talk about the security stories in the news that I haven't covered...
Akamai Firewall for AI: Get Powerful Protection for New LLM App Threats
Protect against LLM attacks such as prompt injection, exfiltration and extraction, and toxic AI outputs with Akamai Firewall for AI...
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
The expansion of large-scale text-to-image diffusion models has raised growing concerns about their potential to generate undesirable or harmful content, ranging from fabricated depictions of public figures to sexually explicit images. To mitigate these risks, prior work has devised machine...
A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content
Large Language Models LLM have made remarkable progress, but concerns about potential biases and harmful content persist. To address these apprehensions, we introduce a practical solution for ensuring LLM's safe and ethical use. Our novel approach focuses on a post-generation correction mechanism...
CISA: Assessing the Risk from Stolen or Diverted Toxic Industrial Chemicals
System About Files News Vote Help | Services API Advertise Contact | Account Join Login ---|---|---...
New Cloud Risk Dashboard: Identifying Toxic Combinations to Drive Faster Remediation
Co-authored by Andrea Ruddy Risks identified within a cloud environment compound to represent a real threat of exploitation. Our cloud risk scoring, introduced recently to insightCloudSec, focuses on these toxic combinations. Toxic combinations are attractive for bad actors who can target multipl...
CFPB’s Proposed Data Rules
In October, the Consumer Financial Protection Bureau CFPB proposed a set of rules that if implemented would transform how financial institutions handle personal data about their customers. The rules put control of that data back in the hands of ordinary Americans, while at the same time undermini...
Expanded Coverage and New Attack Path Visualizations Help Security Teams Prioritize Cloud Risk and Understand Blast Radius
Cloud environments differ in a number of ways from more traditional on-prem environments. From the immense scale and compounding complexity to the rate of change, the cloud creates a host of challenges for security teams to navigate and grapple with. By definition, anything running in the cloud h...
Updates to Layered Context Enable Teams to Quickly Understand Which Risk Signals Are Most Pressing
Layered Context introduced a consolidated view of all security risks insightCloudSec collects from the various layers of a cloud environment. This enabled our customers to go from visibility into individual security risks on a resource, to understanding all of the risks that impacted that resourc...
Uncover and Remediate Toxic Combinations with Attack Path Analysis
Particularly at enterprise scale, it’s not uncommon to have hundreds of thousands of resources running across your cloud environments at any given time. Of course, these resources aren’t running independently. In modern environments, these resources are all interconnected and in many cases...
Malicious Package
Overview @sectest456/toxic-pkg-dont-use is a malicious package. The package's name is based on existing repositories, namespaces, or components used by popular companies in an effort to trick employees into downloading it, also known as 'dependency confusion'. Therefore, you're only vulnerable if...
Spiceworks Input Validation Error Vulnerability
SpiceWorks is a suite of network device management and monitoring software for small and medium-sized businesses from Spiceworks, Inc. An input validation error vulnerability exists in Spiceworks 7.5.7.0, which allows an attacker to render arbitrary links that point to malicious websites with tox...
Spiceworks 输入验证错误漏洞
SpiceWorks is a suite of network device management and monitoring software for small and medium-sized businesses from Spiceworks, Inc. An input validation error vulnerability exists in Spiceworks 7.5.7.0, which allows an attacker to render arbitrary links that point to malicious websites with tox...
