AutoDefense Blog #1982

XHMY · 2024-03-12T21:34:15Z

Why are these changes needed?

A new blog post about our paper using the multi-agent system based on AutoGen to defend the LLM jailbreak attack.

Related issue number

N/A

Checks

I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and test documentation locally.
I've added tests (if relevant) corresponding to the changes introduced in this PR.
I've made sure all auto checks have passed.

XHMY · 2024-03-12T21:36:46Z

@XHMY please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
@microsoft-github-policy-service agree [company="{your company}"]
Options:

(default - no company specified) I have sole ownership of intellectual property rights to my Submissions and I am not making Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
(when company given) I am making Submissions in the course of work for my employer (or my employer has intellectual property rights in my Submissions by contract or applicable law). I have permission from my employer to make Submissions and enter into this Agreement on behalf of my employer. By signing below, the defined term “You” includes me and my employer.
@microsoft-github-policy-service agree company="Microsoft"
Contributor License Agreement

@microsoft-github-policy-service agree

codecov-commenter · 2024-03-12T22:17:28Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 37.83%. Comparing base (83aef3a) to head (2f4c432).

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1982   +/-   ##
=======================================
  Coverage   37.83%   37.83%           
=======================================
  Files          77       77           
  Lines        7766     7766           
  Branches     1663     1663           
=======================================
  Hits         2938     2938           
  Misses       4579     4579           
  Partials      249      249

Flag	Coverage Δ
unittests	`37.81% <ø> (ø)`

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

...te/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx

joshkyh

Thanks for sharing the paper, good luck with the submission! :)

...te/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]>

…uce the two experiments.

...te/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

...te/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

sonichi · 2024-03-28T00:00:51Z

@kevin666aa a kind reminder of the review requested.

yiranwu0

LGTM!

yiranwu0 · 2024-03-30T20:36:42Z

BTW, can you add the paper to Research.md? @XHMY

qingyun-wu

Thanks for the revisions. Looks good now!

* AutoDefense Blog * Update Defense Agency Section * format update * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]> * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]> * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]> * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]> * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]> * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]> * format fix * rename picture, make it informative. Add a overall sentence to introduce the two experiments. * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]> * update Further reading, introduction * update Further reading, introduction * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]> * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]> * Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jailbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]> --------- Co-authored-by: Yiran Wu <[email protected]> Co-authored-by: Joshua Kim <[email protected]>

XHMY added 2 commits March 11, 2024 22:07

AutoDefense Blog

b7c3687

Merge branch 'main' into main

e0fdff9

sonichi requested review from joshkyh, qingyun-wu, yiranwu0 and julianakiseleva March 12, 2024 21:41

Update Defense Agency Section

77d76bc

format update

8ebc326

yiranwu0 reviewed Mar 12, 2024

View reviewed changes

joshkyh reviewed Mar 13, 2024

View reviewed changes

XHMY and others added 10 commits March 13, 2024 13:25

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

1275441

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

cb17911

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]>

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

67e2f9b

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]>

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

a29b0e5

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]>

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

9d88ab8

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]>

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

5d23fea

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Joshua Kim <[email protected]>

format fix

e8de68c

Merge branch 'main' into main

7ae59b0

Merge branch 'main' into main

a9b8c43

rename picture, make it informative. Add a overall sentence to introd…

42d598a

…uce the two experiments.

XHMY requested a review from yiranwu0 March 15, 2024 03:48

yiranwu0 reviewed Mar 15, 2024

View reviewed changes

XHMY and others added 4 commits March 15, 2024 08:23

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

9ecfa88

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

Merge branch 'main' into main

75d0e2f

update Further reading, introduction

aa0d8ef

update Further reading, introduction

caae316

XHMY requested a review from yiranwu0 March 23, 2024 17:14

Merge branch 'main' into main

0396dfd

yiranwu0 reviewed Mar 24, 2024

View reviewed changes

XHMY and others added 4 commits March 24, 2024 16:22

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

29f002a

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

fce2bee

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

Update website/blog/2024-03-11-AutoDefense/Defending LLMs Against Jai…

26a4c95

…lbreak Attacks with AutoDefense.mdx Co-authored-by: Yiran Wu <[email protected]>

Merge branch 'main' into main

8676f40

XHMY requested a review from yiranwu0 March 25, 2024 16:04

sonichi requested a review from JieyuZ2 March 28, 2024 00:01

XHMY and others added 2 commits March 29, 2024 17:18

Merge branch 'main' into main

aa2ef9b

Merge branch 'main' into main

2f4c432

yiranwu0 approved these changes Mar 30, 2024

View reviewed changes

JieyuZ2 approved these changes Mar 30, 2024

View reviewed changes

qingyun-wu approved these changes Mar 30, 2024

View reviewed changes

qingyun-wu added this pull request to the merge queue Mar 30, 2024

Merged via the queue into microsoft:main with commit f795265 Mar 30, 2024
24 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

AutoDefense Blog #1982

AutoDefense Blog #1982

XHMY commented Mar 12, 2024

XHMY commented Mar 12, 2024

codecov-commenter commented Mar 12, 2024 •

edited

Loading

joshkyh left a comment

sonichi commented Mar 28, 2024

yiranwu0 left a comment

yiranwu0 commented Mar 30, 2024

qingyun-wu left a comment

AutoDefense Blog #1982

AutoDefense Blog #1982

Conversation

XHMY commented Mar 12, 2024

Why are these changes needed?

Related issue number

Checks

XHMY commented Mar 12, 2024

codecov-commenter commented Mar 12, 2024 • edited Loading

Codecov Report

joshkyh left a comment

Choose a reason for hiding this comment

sonichi commented Mar 28, 2024

yiranwu0 left a comment

Choose a reason for hiding this comment

yiranwu0 commented Mar 30, 2024

qingyun-wu left a comment

Choose a reason for hiding this comment

codecov-commenter commented Mar 12, 2024 •

edited

Loading