Search Results for "injection"

MiroFish is a next-generation artificial intelligence prediction engine that leverages multi-agent technology and swarm-intelligence simulation to model, simulate, and forecast complex real-world scenarios. The system extracts “seed” information from sources such as breaking news, policy documents, and market signals to construct a high-fidelity digital parallel world populated by thousands of virtual agents with independent memory and behavior rules. Users can inject variables or conditions...

...The library acts as a protective layer between users and language models by analyzing inputs and outputs before they reach or leave the model. It includes scanning mechanisms that detect malicious prompts, prompt injection attempts, toxic content, and other harmful inputs that could compromise AI systems. The toolkit also helps prevent sensitive information leaks by identifying secrets such as API keys or credentials before they are processed by the model. LLM Guard supports both input and output filtering pipelines, allowing developers to sanitize prompts and validate generated responses in real time. ...

RecAI is an open-source research platform developed by Microsoft to explore how large language models can be integrated into modern recommender systems. Traditional recommender systems rely on structured behavioral data such as user interactions and item embeddings, while large language models excel at understanding language and reasoning about user preferences. RecAI aims to bridge these two domains by creating architectures and training methods that allow LLMs to function as intelligent...

FuzzyAI is an open-source fuzzing framework designed to test the security and reliability of large language model applications. The tool automates the process of generating adversarial prompts and input variations to identify vulnerabilities such as jailbreaks, prompt injections, or unsafe model responses. It allows developers and security researchers to systematically evaluate the robustness of LLM-based systems by simulating a wide range of malicious or unexpected inputs. The framework can...

AICGSecEval is an open-source benchmark framework designed to evaluate the security of code generated by artificial intelligence systems. The project was developed to address concerns that AI-assisted programming tools may produce insecure code containing vulnerabilities such as injection flaws or unsafe logic. The framework constructs evaluation tasks based on real-world software repositories and known vulnerability cases derived from CVE records. By simulating realistic development scenarios, the benchmark assesses how well AI code generation systems handle security-sensitive programming tasks. AICGSecEval combines static and dynamic evaluation techniques to analyze generated code for vulnerabilities and functional correctness. ...

Text-to-LoRA is a research project that introduces a method for dynamically adapting large language models using hypernetworks that generate LoRA parameters directly from textual descriptions. Instead of training a new LoRA adapter for every task or dataset, the system can produce task-specific adaptations based solely on a text description of the desired capability. This approach enables models to rapidly internalize new contextual knowledge without performing traditional fine-tuning steps....

promptmap is an automated security scanner for custom LLM applications that focuses on prompt injection and related attack classes. The project supports both white-box and black-box testing, which means it can either run tests directly against a known model and system prompt configuration or attack an external HTTP endpoint without internal access. Its scanning workflow uses a dual-LLM architecture in which one model acts as the target being tested and another acts as a controller that evaluates whether an attack succeeded. ...