Skip to content
KitploitKITPLOIT
ToolsExploitsBlog
Log in
Submit
ToolsExploitsBlog
Submit

Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!

Kitploit is a directory of hacking, cybersecurity, and pentesting tools. Discover the latest project updates to find vulnerabilities, analyze systems, automate testing, and strengthen your security.

FeedsContactPrivacy© 2026 Kitploit

Tool Directory

Categories

View all categories
Loading categories
Exponentiated-Gradient-Descent-LLM-Attack — A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique. | Kitploit
Tools/GitHubGitHub/sbamit/exponentiated-gradient-descent-llm-attack
Machine LearningPapers & ResearchAI SecurityAdversarial Attack
GitHubsbamit/exponentiated-gradient-descent-llm-attack

Exponentiated-Gradient-Descent-LLM-Attack

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

View Repository
Share
413111 months agoNot yet reviewed

Change Readme File.

This is a Project that explores the Exponentiated Gradient Descent optimizaiton method to produce adversarial suffix to attack algined Large Language Models. The method is shown to be effective on Llama-2 chat model with 7 Billion parameters.

To run pgd script on a number of behaviors(i.e., 20), execute the following command in the shell. python run_pgd.py
--input_file "/home/samuel/research/llmattacks/llm-attacks/data/advbench/harmful_behaviors.csv"
--output_file "./JSON_Files/PGD_AdvBench_Llama2.jsonl"
--model "Llama2"
--dataset_name "AdvBench"
--num_behaviors 20

Next target is to build similar pipeline for the EGD with Adam optim script.

Download Tool

Most Popular

View all →

Discover the most used tools by our community.

  • 1

    OsintHunter

    letox4/osinthunter

    🎯 The ultimate OSINT toolkit: investigation graph, confidence scoring, alias families, map, timeline and reports. 49 modules, 400+ sites, no API keys required.

    795
  • 2

    ghostlock-app

    yukonga/ghostlock-app

    GhostLock One-Tap Execution App (CVE-2026-43499)

    520
  • 3

    ARTEX

    baarai/artex

    LLM multi-agent autonomous penetration testing platform with planner/worker agents, asset and exploration graphs, MITM traffic recording, and vulnerability retesting.

    439
  • 4

    redforge

    cybersecurity91/redforge

    Browser-side red team toolkit with 102 offline tools for recon, payload generation, credential attacks, crypto, encoding and engagement reporting.

    346
  • 5

    looking-glass

    anonghosty/looking-glass

    CSIRT platform that ingests Shadowserver reports into MongoDB and replays them as interactive maps, analysis, findings, advisories and executive dashboards.

    267
  • 6

    CyberStrikeAI

    ed1s0nz/cyberstrikeai

    The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

    264

Explore all tools

Browse our collection of tools

View all tools →