HKU-TASR / Imperio
[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.
☆41Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for Imperio
- Implementation of BEAST adversarial attack for language models (ICML 2024)☆73Updated 6 months ago
- Enumerate SSN (System Service Numbers or Syscall ID) and syscall instruction address in ntdll module by parsing the PEB of the current pr…☆18Updated 9 months ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆95Updated 9 months ago
- ☆28Updated last year
- Exploit Proof-of-Concept code for XAMPP v3.3.0 — '.ini' Buffer Overflow (Unicode + SEH)☆14Updated last year
- FWT is a security analysis and file monitoring tool that utilizes Sysmon events.☆24Updated 4 months ago
- Cobalt Strike BOFS☆16Updated 11 months ago
- DLink DIR-846 Authenticated Remote Code Execution☆18Updated last year
- Advanced test for proxy & waf☆12Updated 2 months ago
- Generate AES128 and AES256 Kerberos keys from a given username, password, and realm☆15Updated 2 months ago
- ☆50Updated 7 months ago
- A folder to serve tools from during PT/Red Team engagements. Contains common executables and scripts for privesc, recon, pivoting and CVE…☆15Updated 8 months ago
- POC for CVE-2024-3183 (FreeIPA Rosting)☆18Updated 3 months ago
- CVE-2024-29895 PoC - Exploiting remote command execution in Cacti servers using the 1.3.X DEV branch builds☆21Updated 6 months ago
- Updated Exploit - pfBlockerNG <= 2.1.4_26 Unauth RCE (CVE-2022-31814)☆23Updated 3 months ago
- Burp extension used to snip any header from all the requests.☆22Updated last year
- Kubernetes, Clusters and Dockers Enumeration in GCP and AWS environments☆12Updated 11 months ago
- aiohttp LFI (CVE-2024-23334)☆22Updated 8 months ago
- ☆35Updated 11 months ago
- Mass Exploit - CVE-2024-29824 - Ivanti EPM - Remote Code Execution (RCE)☆28Updated 4 months ago
- Tool for scanning domains for .git directories.☆13Updated last year
- A BrainF*ck Inspired Shell Obfuscation Proof-of-Concept☆14Updated 8 months ago
- ☆10Updated 3 months ago
- Stage 1: Sensitive Email/Chat Classification for Adversary Agent Emulation (espionage). This project is meant to extend Red Reaper v1 whi…☆23Updated 3 months ago
- A graphical automation to monitor if backdoors/default settings are still active on the compromised machines over time.☆43Updated 8 months ago
- Monitor your target continuously for new subdomains!☆26Updated last year
- ☆16Updated last year