Lucene search
+L

1491 matches found

Packet Storm News
Packet Storm News
added 2025/06/04 12:0 a.m.7 views

Watermarking Degrades Alignment in Language Models: Analysis and Mitigation

Watermarking techniques for large language models LLMs can significantly impact output quality, yet their effects on truthfulness, safety, and helpfulness remain critically underexamined. This paper presents a systematic analysis of how two popular watermarking approaches-Gumbel and KGW-affect...

7AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/06/03 7:20 a.m.12 views

Microsoft and CrowdStrike Launch Shared Threat Actor Glossary to Cut Attribution Confusion

Microsoft and CrowdStrike have announced that they are teaming up to align their individual threat actor taxonomies by publishing a new joint threat actor mapping. "By mapping where our knowledge of these actors align, we will provide security professionals with the ability to connect insights...

7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/06/03 12:0 a.m.20 views

BitBypass: a New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage

The inherent risk of generating harmful and unsafe content by Large Language Models LLMs, has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and red-teaming were developed for ensuring the safety alignme...

7.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/31 12:0 a.m.7 views

Video Signature: In-Generation Watermarking for Latent Video Diffusion Models

The rapid development of Artificial Intelligence Generated Content AIGC has led to significant progress in video generation but also raises serious concerns about intellectual property protection and reliable content tracing. Watermarking is a widely adopted solution to this issue, but existing...

6.8AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/30 12:0 a.m.6 views

Safety Alignment Can Be Not Superficial with Explicit Safety Signals

Recent studies on the safety alignment of large language models LLMs have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies generally fail to offer actionable solutions beyond data...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/29 12:0 a.m.10 views

Disrupting Vision-Language Model-Driven Navigation Services Via Adversarial Object Fusion

We present Adversarial Object Fusion AdvOF, a novel attack framework targeting vision-and-language navigation VLN agents in service-oriented environments by generating adversarial 3D objects. While foundational models like Large Language Models LLMs and Vision Language Models VLMs have enhanced...

6.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/29 12:0 a.m.9 views

SafeCOMM: What about Safety Alignment in Fine-Tuned Telecom Large Language Models?

Fine-tuning large language models LLMs for telecom tasks and datasets is a common practice to adapt general-purpose models to the telecom domain. However, little attention has been paid to how this process may compromise model safety. Recent research has shown that even benign fine-tuning can...

7.3AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/28 12:0 a.m.6 views

GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance

DNA, encoding genetic instructions for almost all living organisms, fuels groundbreaking advances in genomics and synthetic biology. Recently, DNA Foundation Models have achieved success in designing synthetic functional DNA sequences, even whole genomes, but their susceptibility to jailbreaking...

7.5AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/27 12:0 a.m.25 views

M3S-UPD: Efficient Multi-Stage Self-Supervised Learning for Fine-Grained Encrypted Traffic Classification with Unknown Pattern Discovery

The growing complexity of encrypted network traffic presents dual challenges for modern network management: accurate multiclass classification of known applications and reliable detection of unknown traffic patterns. Although deep learning models show promise in controlled environments, their...

6.7AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2025/05/26 12:0 a.m.7 views

Lifelong Safety Alignment for Language Models

LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more critical to prepare LLMs for unseen attacks that may arise duri...

7.5AI score
SaveExploits0
RedhatCVE
RedhatCVE
added 2025/05/23 8:15 a.m.9 views

CVE-2024-9127

The Super Testimonials plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the ‘alignment’ parameter in all versions up to, and including, 3.0.0 due to insufficient input sanitization and output escaping. This makes it possible for authenticated attackers, with Contributor-level...

6.4CVSS5AI score0.00332EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/23 3:28 a.m.9 views

CVE-2023-37304

An issue was discovered in the DoubleWiki extension for MediaWiki through 1.39.3. includes/DoubleWiki.php allows XSS via the column alignment feature...

5.4CVSS5.8AI score0.00497EPSS
SaveExploits1References1
RedhatCVE
RedhatCVE
added 2025/05/22 9:19 p.m.15 views

CVE-2021-23253

Opera Mini for Android below 53.1 displays URL left-aligned in the address field. This allows a malicious attacker to craft a URL with a long domain name, e.g. www.safe.opera.com.attacker.com. With the URL being left-aligned, the user will only see the front part e.g. www.safe.opera.com… The exac...

5.3CVSS6.8AI score0.00751EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/22 7:38 p.m.7 views

CVE-2021-30275

Possible integer overflow in page alignment interface due to lack of address and size validation before alignment in Snapdragon Auto, Snapdragon Compute, Snapdragon Connectivity, Snapdragon Consumer IOT, Snapdragon Industrial IOT, Snapdragon Voice & Music, Snapdragon Wired Infrastructure and...

9.3CVSS7.9AI score0.00154EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/22 6:13 p.m.13 views

CVE-2021-1974

Possible buffer over read due to lack of alignment between map or unmap length of IPA SMMU and WLAN SMMU in Snapdragon Auto, Snapdragon Compute, Snapdragon Connectivity, Snapdragon Consumer IOT, Snapdragon Industrial IOT, Snapdragon Mobile, Snapdragon Wearables, Snapdragon Wired Infrastructure an...

7.5CVSS7.3AI score0.00587EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/22 5:37 p.m.9 views

CVE-2020-36519

Mimecast Email Security before 2020-01-10 allows any admin to spoof any domain, and pass DMARC alignment via SPF. This occurs through misuse of the address rewrite feature. The domain being spoofed must be a customer in the Mimecast grid from which the spoofing occurs...

4.9CVSS6.8AI score0.00815EPSS
SaveExploits1
RedhatCVE
RedhatCVE
added 2025/05/22 5:24 p.m.8 views

CVE-2020-11161

Out-of-bounds memory access can occur while calculating alignment requirements for a negative width from external components in Snapdragon Auto, Snapdragon Compute, Snapdragon Connectivity, Snapdragon Consumer IOT, Snapdragon Industrial IOT, Snapdragon Mobile, Snapdragon Voice & Music...

7.1CVSS7.2AI score0.00146EPSS
SaveExploits0References1
RedhatCVE
RedhatCVE
added 2025/05/22 4:19 p.m.14 views

CVE-2020-25796

An issue was discovered in the sized-chunks crate through 0.6.2 for Rust. In the InlineArray implementation, an unaligned reference may be generated for a type that has a large alignment requirement...

7.5CVSS6.7AI score0.01634EPSS
SaveExploits1
RedhatCVE
RedhatCVE
added 2025/05/22 4:16 p.m.9 views

CVE-2020-25576

An issue was discovered in the randcore crate before 0.4.2 for Rust. Casting of byte slices to integer slices mishandles alignment constraints...

9.8CVSS6.7AI score0.01558EPSS
SaveExploits0
RedhatCVE
RedhatCVE
added 2025/05/22 3:34 p.m.9 views

CVE-2020-36433

An issue was discovered in the chunky crate through 2020-08-25 for Rust. The Chunk API does not honor an alignment requirement...

7.5CVSS6.9AI score0.00915EPSS
SaveExploits0
Rows per page
Query Builder