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...

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...

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...

Unlearning Isn'T Deletion: Investigating Reversibility of Machine Unlearning in LLMs

Unlearning in large language models LLMs is intended to remove the influence of specific data, yet current evaluations rely heavily on token-level metrics such as accuracy and perplexity. We show that these metrics can be misleading: models often appear to forget, but their original behavior can ...

MTSA: Multi-Turn Safety Alignment for LLMs through Multi-Round Red-Teaming

Whitepaper called MTSA: Multi-Turn Safety Alignment For LLMs Through Multi-Round Red-Teaming...

CVE-2005-3753

Linux kernel before after 2.6.12 and before 2.6.13.1 might allow attackers to cause a denial of service Oops via certain IPSec packets that cause alignment problems in standard multi-block cipher processors. NOTE: it is not clear whether this issue can be triggered by an attacker...

SUSE CVE-2025-37922

In the Linux kernel, the following vulnerability has been resolved: book3s64/radix : Align section vmemmap start address to PAGESIZE A vmemmap altmap is a device-provided region used to provide backing storage for struct pages. For each namespace, the altmap should belong to that same namespace. ...

Alignment under Pressure: the Case for Informed Adversaries When Evaluating LLM Defenses

Large language models LLMs are rapidly deployed in real-world applications ranging from chatbots to agentic systems. Alignment is one of the main approaches used to defend against attacks such as prompt injection and jailbreaks. Recent defenses report near-zero Attack Success Rates ASR even again...