1491 matches found
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...