Awesome-LLMs-for-Vulnerability-Detection

Awesome Large Language Models for Vulnerability Detection A curated list of papers, projects, and agent skills on using LLMs for vulnerability detection and discovery. 📄 Papers Only showing 2025 and later. For earlier work, see Papers Archive 2024 and earlier. Title| Venue| Year| Paper| Github...

Perturbed-Embedding-Vectors

Jailbreaking Open-Weight LLMs via Random Embedding Perturbations: runs, labels and code Code and data for the paper Jailbreaking Open-Weight LLMs via Random Embedding Perturbations. Link to the pre-print of the paper- https://arxiv.org/abs/2610.07125 Authored by the amazing people of the...

Securiscan

Securiscan Securiscan Securiscan is a robust, lightweight, and native standard-library security triage engine built to analyze vulnerabilities across Web Applications, APIs, LLMs, and Mobile Packages completely using Python standard built-ins. 🚀 Core Execution Modes 1. Passive External Inspection...

Understanding and Mitigating Role Spoofing in LLMs

Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it has recently been observed that LLMs can exhibit role confusion Ye et al., 2026, where models attribute the source of text based on its style instea...

Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-Of-Experts LLMs

As Mixture-of-Experts MoE large language models are increasingly deployed in distributed environments, from federated learning to edge-cloud systems, their architecture harbors an underexplored landscape of security vulnerabilities. Moving beyond textual analysis, we uncover structural...

Can Open Be Too Open? on the Security and Trustworthiness of Fully Transparent LLMs

There are different levels of transparency for LLMs: open weights, open data, and/or open pipeline. Recently, more interest has emerged in fully transparent LLMs, i.e., LLMs with fully open weights, data, and training pipeline. Drawing analogies to other fields such as software security, it is...

llm-security

New: Demonstrating Indirect Injection attacks on Bing Chat Compromising LLMs using Indirect Prompt Injection "... a language model is a Turing-complete weird machine running programs written in natural language; when you do retrieval, you are not 'plugging updated facts into your AI', you are...

TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs

As large language models LLMs face growing demands for data removal driven by regulatory compliance, copyright concerns, and privacy protection, approximate unlearning has emerged as a practical alternative to expensive full retraining. In practice, pre- and post-unlearning model snapshots are...

Data-Void Exploits in Web-Searching LLMs

Web-searching Large Language Models LLMs have changed how users seek online information: instead of sifting through ranked lists of links, users read synthesized answers. This shift creates a new LLM vulnerability: a data-void exploit. Disinformers publish their narratives in search spaces where...

Privacy in Context Is Being Overlooked in the Age of General-Purpose LLMs

As large language models LLMs continue to grow in scope and capability, privacy concerns are on the rise. Since users increasingly interact with a single general-purpose system across many distinct contexts, there is a natural tendency to pursue a one-size-fits-all solution to privacy...

Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts

LLMs increasingly operate over mixed-sensitivity contexts, where they must reason over information ranging from public to confidential while disclosing only what the user is authorised to receive. Existing approaches enforce access control as a binary decision: either fully answering or refusing,...

Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams

Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermeasures impose no resource cost on perpetrators. Strategic scam-baiting, in which automated agents engage scammers to deplete their operational capacity, offers a proactive...

When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMs

Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code models spanning 6.7B-15B parameters on C programs using three datasets DELTASECOMMITS, SVEN, and PRECISE-BUGS, comparing two diagnostic tasks on the...

RedDarwin: Evolving Jailbreak Skills against Frontier LLMs

Red teaming must continually adapt as frontier LLM safeguards evolve, yet existing approaches largely search for adversarial prompts or optimize within fixed attack procedures. We observe that even when an attack becomes ineffective, its underlying mechanisms can remain useful and can be revised ...

Diagnose Before You Refine: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak Attacks

Automated jailbreak attacks rely on evaluation feedback to optimize adversarial prompts, but existing methods often lack fine-grained diagnostic information. We propose Jev-Guided Strategy Bandit JSB, a query-based jailbreak framework that leverages multi-dimensional probabilistic feedback to gui...

LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense

Large language models LLMs perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override user intent. Existing defenses remain limited by model fine-tuning requirements, vulnerability to...

Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII

The robustness of Personally Identifiable Information PII protection in Large Language Models LLMs is a critical concern, yet the risks associated with cross-lingual data extraction remain under-explored. This study evaluates the vulnerability of English-centric and multilingual models to Trainin...

Jailbreaking Open-Weight LLMs Via Random Embedding Perturbations

While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important concern. One key feature is the ability to refuse or deflect harmful, malicious, or insensitive prompts. In this paper, we expose safety vulnerabiliti...

Reflections and Fragments: Securing LLMs against Sequential Mosaic Attacks

Self-play red-teaming improves language-model safety by pitting attacker and defender roles against each other in a zero-sum game. However, real adversaries increasingly use mosaic attacks: multi-turn sequences whose individual fragments are innocuous in isolation yet assemble into a harmful...

Reactivating Alignment: Defending LLMs from Jailbreaks Via Intention-Aware Input-Output Matching

Large language models LLMs remain vulnerable to jailbreak attacks that conceal harmful intent within complex adversarial prompts. Existing defenses primarily rely on input perturbation or harmful-output suppression, but they rarely model where malicious intent resides, resulting in brittle...