Lucene search
+L

47 matches found

Packet Storm News
Packet Storm News
added 2025/05/20 12:00 a.m.4 views

Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion

Although large language models LLMs have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or objectionable content. Researchers study jailbreak attacks to...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/14 12:00 a.m.9 views

Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent

As Large Language Models LLMs are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from human feedback RLHF, they are still vulnerable to jailbreakin...

7.4AI score
SaveExploits0
Trend Micro Simply Security
Trend Micro Simply Security
added 2025/05/01 12:00 a.m.14 views

Exploring PLeak: An Algorithmic Method for System Prompt Leakage

What is PLeak, and what are the risks associated with it? We explored this algorithmic technique and how it can be used to jailbreak LLMs, which could be leveraged by threat actors to manipulate systems and steal sensitive data...

7.1AI score
SaveExploits0
OSV
OSV
added 2025/03/19 4:15 p.m.7 views

PYSEC-2025-63

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code...

9CVSS8.3AI score0.00728EPSS
SaveExploits0References3
CVE
CVE
added 2025/03/19 3:31 p.m.328 views

CVE-2025-29770

CVE-2025-29770 affects vLLM’s guided_decoding outlines backend. The vulnerability arises because outlines_logits_processors.py unconditionally uses outlines’ on-disk grammar cache, enabling a malicious user to send many short decoding requests with unique schemas and exhaust the filesystem, causi...

6.5CVSS6.4AI score0.00453EPSS
SaveExploits0References3Affected Software1
Schneier on Security
Schneier on Security
added 2025/02/05 12:03 p.m.14 views

On Generative AI Security

Microsoft's AI Red Team just published "Lessons from Red Teaming 100 Generative AI Products." Their blog post lists "three takeaways," but the eight lessons in the report itself are more useful: 1. Understand what the system can do and where it is applied. 2. You don't have to compute gradients t...

7.5AI score
SaveExploits0
Akamai Blog
Akamai Blog
added 2024/11/04 2:00 p.m.13 views

Exploring Artificial Intelligence: Is AI Overhyped?

Dive into AI technologies like inference, deep learning, and generative models to learn how LLMs and AI are transforming cybersecurity and tech industries...

7.3AI score
SaveExploits0
GoogleProjectZero
GoogleProjectZero
added 2024/11/01 12:00 a.m.163 views

From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code

Posted by the Big Sleep team Introduction In our previous post, Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models, we introduced our framework for large-language-model-assisted vulnerability research and demonstrated its potential by improving the state-of-the-a...

7.7AI score
SaveExploits0
Talos Blog
Talos Blog
added 2024/10/25 2:09 p.m.10 views

How LLMs could help defenders write better and faster detection

Most users will associate large language models LLMs like ChatGPT with answering basic questions or helping to write basics lines of text. But could these tools actually help defenders in the cybersecurity industry write more effective detection content? Several security researchers from across...

7.2AI score
SaveExploits0
Wiz blog
Wiz blog
added 2024/06/20 3:43 p.m.17 views

GenAI risks to be aware of — and prepare for — according to Gartner®

The deployment of GenAI, LLMs, and chat interfaces expands potential attack surfaces and poses increased security threats...

7.4AI score
SaveExploits0
GoogleProjectZero
GoogleProjectZero
added 2024/06/20 12:00 a.m.164 views

Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models

Posted by Sergei Glazunov and Mark Brand, Google Project Zero Introduction At Project Zero, we constantly seek to expand the scope and effectiveness of our vulnerability research. Though much of our work still relies on traditional methods like manual source code audits and reverse engineering,...

7.8AI score
SaveExploits0
Schneier on Security
Schneier on Security
added 2024/06/11 11:02 a.m.25 views

LLMs Acting Deceptively

New research: "Deception abilities emerged in large language models": Abstract: Large language models LLMs are currently at the forefront of intertwining AI systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady...

7.3AI score
SaveExploits0
The Hacker News
The Hacker News
added 2024/06/03 10:56 a.m.41 views

SASE Threat Report: 8 Key Findings for Enterprise Security

Threat actors are evolving, yet Cyber Threat Intelligence CTI remains confined to each isolated point solution. Organizations require a holistic analysis across external data, inbound and outbound threats and network activity. This will enable evaluating the true state of cybersecurity in the...

10CVSS10AI score0.99999EPSS
SaveExploits360
CVE
CVE
added 2024/05/16 9:03 a.m.93 views

CVE-2024-4181

The CVE-2024-4181 issue affects llama_index (RunGptLLM class) version 0.9.47 used by RunGpt framework to connect to LLMs. Root cause: unsafe use of eval enabling a malicious or compromised LLM hosting provider to run arbitrary commands on a client machine. Impact statements in sources indicate th...

8.8CVSS7.9AI score0.02118EPSS
SaveExploits1References2Affected Software1
Spring Security Advisories
Spring Security Advisories
added 2024/04/19 12:00 a.m.32 views

Spring AI - Multimodality - Orbis Sensualium Pictus

Humans process knowledge, simultaneously across multiple modes of data inputs. The way we learn, our experiences are all multimodal. We don't have just vision, just audio and just text. These foundational principles of learning were articulated by the father of modern education John Amos Comenius...

7AI score
SaveExploits0
NVD
NVD
added 2024/04/16 3:15 p.m.14 views

CVE-2024-30256

Open WebUI is a user-friendly WebUI for LLMs. Open-webui is vulnerable to authenticated blind server-side request forgery. This vulnerability is fixed in 0.1.117...

6.4CVSS6.2AI score0.00412EPSS
SaveExploits1References2
CVE
CVE
added 2024/04/16 2:24 p.m.73 views

CVE-2024-30256

CVE-2024-30256 affects Open WebUI prior to version 0.1.117. The vulnerability is an authenticated blind server-side request forgery (SSRF) in the backend, specifically in the function download_file_stream() inside Open WebUI’s backend/apps/web/routers/utils.py, exploitable via the url parameter. ...

6.4CVSS6.5AI score0.00412EPSS
SaveExploits1References2Affected Software1
The Hacker News
The Hacker News
added 2024/03/20 11:27 a.m.57 views

Generative AI Security - Secure Your Business in a World Powered by LLMs

Did you know that 79% of organizations are already leveraging Generative AI technologies? Much like the internet defined the 90s and the cloud revolutionized the 2010s, we are now in the era of Large Language Models LLMs and Generative AI. The potential of Generative AI is immense, yet it brings...

6.9AI score
SaveExploits0
Schneier on Security
Schneier on Security
added 2024/03/12 11:12 a.m.12 views

Jailbreaking LLMs with ASCII Art

Researchers have demonstrated that putting words in ASCII art can cause LLMs--GPT-3.5, GPT-4, Gemini, Claude, and Llama2--to ignore their safety instructions. Research paper...

7.5AI score
SaveExploits0
Schneier on Security
Schneier on Security
added 2024/03/11 11:01 a.m.24 views

Using LLMs to Unredact Text

Initial results in using LLMs to unredact text based on the size of the individual-word redaction rectangles. This feels like something that a specialized ML system could be trained on...

7.2AI score
SaveExploits0
Rows per page
Query Builder