Explore tweets tagged as #PromptInjection
@Pethuraj
Pethuraj M
6 days
๐๐ซ๐จ๐ฆ๐ฉ๐ญ ๐ˆ๐ง๐ฃ๐ž๐œ๐ญ๐ข๐จ๐ง ๐š๐ญ๐ญ๐š๐œ๐ค ๐ฅ๐š๐›๐ฌ ๐ฐ๐ข๐ญ๐ก ๐ซ๐ž๐š๐ฅ-๐ญ๐ข๐ฆ๐ž ๐Ÿ๐ž๐ž๐๐›๐š๐œ๐ค ๐š๐ง๐ ๐ซ๐ž๐Ÿ๐ข๐ง๐ž ๐ฒ๐จ๐ฎ๐ซ ๐€๐ˆ ๐ข๐ง๐ญ๐ž๐ซ๐š๐œ๐ญ๐ข๐จ๐ง๐ฌ ๐จ๐ง ๐ญ๐ก๐ž ๐ ๐จ. Check it out here: ๐Ÿ”— #AI #CyberSecurity #AISecurity #PromptInjection
Tweet media one
1
3
8
@aistartupfren
Lan ๐ŸŒŠ
1 month
AI prompt injection to filter AI bots #ai #aistartup #promptinjection
0
1
4
@neptune_ai
neptune.ai
22 days
[New on our blog] Understanding #PromptInjection: Risks, Methods, and Defense Measures . Author: Soumya Shaw.Reading time: 13 min. โ€”. Full article:
Tweet media one
0
0
0
@allhands_ai
All Hands AI
20 days
Mitigating prompt-injection in software agents โ€ผ๏ธ. The Good ๐Ÿ˜‡.The Bad ๐Ÿ˜ˆ.And a playbook on how to stay safe ๐Ÿฆพ. Read to learn more๐Ÿ‘€. #AIsecurity #LLMAgents #PromptInjection
Tweet media one
2
3
23
@pyotam2
Yotam Perkal
2 years
I've managed to get GPT-4 to predict my future - and believe it or not, it even came true! ๐Ÿ˜‰๐Ÿ‘‡. What's interesting about this File Name #PromptInjection technique is its delayed trigger, allowing activation at any stage of the conversation. Nice find @elder_plinius!
Tweet media one
0
1
2
@welcomeai
Welcome.AI
2 months
Guardrails, Prompt Injection, Evaluation, Human-in-the-Loop โ€” essential safeguards for deploying GenAI systems.#Guardrails #PromptInjection #Evaluation #HumanInTheLoop #HITL #AItrust #AISafety #AIEvaluation #LLM #promptengineering #systemprompt #outputfiltering #biasdetection
2
0
2
@archie_jackson
๐Ÿ”บArchie Jackson ๐Ÿ”บ
19 days
๐Ÿ‘‰ Subscribe to my newsletter and read the details article - ๐Ÿšจ THE AI HACK THAT'S BREAKING THE INTERNET: The Prompt Injection Pandemic. ๐Ÿ“• > #PromptInjection #AIHack #OpenAI #ChatGPT #CyberSecurity #DataBreach #AIThreats #PromptInjection #AIHack #ChatGPT
1
0
1
@evrnyalcin
Evren
10 months
With the new ChatGPT Search feature, Indirect Prompt Injection occurs when you directly visit the URL. It also wasnโ€™t visible in the sources. ๐Ÿ‘ฝ. #promptinjection #chatgpt
Tweet media one
1
1
10
@chemaalonso
Chema Alonso
14 days
El lado del mal - Hacking IA: Indirect Prompt Injection en Perplexity Comet #PromptInjection #Perplexity #Comet #IA #AI #Hacking #Pentest #Pentesting #InteligenciaArtificial #AgenticAI
Tweet media one
3
136
158
@PromptInjection
Prompt Injection
13 days
Gemma 3 270M fine-tune on Windows with @UnslothAI. It worked! ๐Ÿฅณ
Tweet media one
7
21
237
@geek_metaverse
๐Ÿš€๐ŸŒ• Geek Metaverse ๐Ÿš€๐ŸŒ•
1 month
What is Prompt Injection? Risks, Examples, and How to Prevent Attacks. #ai #artificialintelligence #prompt #promptengineering #promptinjection #hacker.
0
0
0
@archie_jackson
๐Ÿ”บArchie Jackson ๐Ÿ”บ
17 days
๐Ÿ”ฅ How Hackers Weaponize Language ๐Ÿง .#AIHacking #PromptInjection #CyberAwareness #AIChatbots #DataSecurity #Infosec.๐Ÿ‘‰ Subscribe to my newsletter and read the details article - ๐Ÿšจ THE AI HACK THAT'S BREAKING THE INTERNET: The Prompt Injection Pandemic.๐Ÿ“• >
2
0
2
@bjgreenberg
Brian Greenberg
14 hours
๐Ÿคฆ๐Ÿปโ€โ™‚๏ธ Oh great, another new AI attack surface. prompt injection hiding in images. Looks harmless, but resized images can trigger hidden commands & even exfiltrate data. ๐Ÿ” Needs layered defenses. #AIsecurity #promptinjection #cybersecurity.
2
0
0
@Pethuraj
Pethuraj M
7 days
๐Ÿค–๐Ÿ’ฅ Prompt injection is still one of the most underestimated risks in AI development. If you're building with or around LLMs, this is worth a read:. ๐Ÿ”— #AIsecurity #PromptInjection #AppSec #LLMSecurity #CyberSecurity #AIrisks
Tweet media one
0
0
3
@sec_phoenix
Phoenix Security - Appsec Phoenix - Cloud Security
1 month
AI tools are useful, but still need control. A recent AWS Copilot incident revealed "malicious" attempts at supply chain attacks, leading to disruptive actions. #AIsecurity #PromptInjection
0
0
1
@influencer_seo
Bennett | Build In Public | AI SAAS SEO Founder
1 year
Posted on Upwork and one of my questions used prompt injection to only have LLMs reply as a pirate .#upwork #promptinjection
Tweet media one
0
0
0
@chemaalonso
Chema Alonso
13 days
El lado del mal - PROMISQROUTE para GPT-5: Un ataque de downgrade forzando el Routing para hacer Jailbreak #IA #AI #Jailbreak #PromptInjection #ChatGPT #GPT #OpenAI #bug #Hacking #Pentest #Pentesting #InteligenciaArtificial
Tweet media one
3
135
168
@VerSprite
VerSprite Cybersecurity Services
14 hours
No model is immune. Even ChatGPT-4o and Copilot can be steered under the right conditions. Read our findings:.#LLMSecurity #PromptInjection #AIExploitation #CyberThreats.
0
0
1
@archie_jackson
๐Ÿ”บArchie Jackson ๐Ÿ”บ
16 days
Jason Haddixโ€™s AI Attack Taxonomy.#JasonHaddix #AIHack #ArcanumInfoSec #PromptInjection #CyberSecurity #ArcanumInfoSec #Infosec.๐Ÿ‘‰ Subscribe to my newsletter and read the details article - ๐Ÿšจ THE AI HACK THAT'S BREAKING THE INTERNET: The Prompt Injection Pandemic.๐Ÿ“• >
0
0
1